© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12694
    Prev
    Next
    INDEX
    Explanations

    lists and structures

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on interface‐style step-by‐step instructions, i.e. imperative UI/action words (open, select, enter, click, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    instructional or procedural text, particularly steps in how-to guides and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    instructions and UI-oriented text about user actions and credentials, especially references to form fields/keys and lines ending in question-style punctuation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     દરેક
    0.65
    >∕
    0.64
    धनों
    0.64
    वण्यासाठी
    0.63
     മഴ
    0.62
    voren
    0.61
    淵
    0.61
     Jeux
    0.60
     ночь
    0.60
    一夜
    0.60
    POSITIVE LOGITS
     VARCHAR
    0.73
     isset
    0.72
     varchar
    0.70
    ક્ટર
    0.66
     হিসেবে
    0.63
     определяется
    0.62
     ifelse
    0.61
     unspecified
    0.61
     specified
    0.61
    はもちろん
    0.61
    Activations Density 0.490%

    No Known Activations