© 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. 15817
    Prev
    Next
    INDEX
    Explanations

    `Builder` `Add`

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

    The neuron fires on words that express subjective evaluation or commentary—i.e. adjectives and verbs used to give an opinion or judgment.

    oai_token-act-pair · o4-miniTriggered 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
    ре
    0.80
     incite
    0.79
    re
    0.77
    с
    0.77
    ра
    0.76
     دقائق
    0.74
     võivad
    0.73
    don
    0.71
     shouldn
    0.71
    shoes
    0.71
    POSITIVE LOGITS
     Zeit
    0.79
     осуществ
    0.76
     টাইমস
    0.75
    트워크
    0.75
     해당하는
    0.75
    язви
    0.74
     novelist
    0.74
    Ы
    0.74
     Witt
    0.73
    꺼
    0.73
    Activations Density 0.000%

    No Known Activations