© 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. 322
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron strongly activates on common nouns that denote actions, events, or other abstract “things” (e.g. task, question, crime, act, information, feeling).

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

    nouns related to tasks, activities, or things to be done.

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

    abstract nouns denoting actions, events, or intangible concepts (often nominalizations, sometimes in plural form).

    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
    '
    0.33
    4
    0.30
    2
    0.29
     modern
    0.26
    recent
    0.26
     alternatives
    0.26
    9
    0.26
    近年
    0.25
     actuel
    0.25
    7
    0.25
    POSITIVE LOGITS
     mientras
    0.40
     sambil
    0.40
     terwijl
    0.39
     и
    0.38
     και
    0.38
     mentre
    0.38
    やお
    0.38
     și
    0.37
     enquanto
    0.37
     এবং
    0.36
    Activations Density 0.000%

    No Known Activations