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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9463
    Prev
    Next
    INDEX
    Explanations

    specific terms followed by context

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

    This neuron fires on positive evaluative language—words and phrases that praise or compliment something.

    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
    各类
    0.89
     இயந்திர
    0.79
    支払い
    0.79
    🧑
    0.78
     প্রত্যেক
    0.77
    上帝
    0.77
     rudimentary
    0.77
     অপরের
    0.75
    precio
    0.75
     jeder
    0.74
    POSITIVE LOGITS
    !
    1.03
    (
    0.91
    /
    0.91
     (
    0.89
    .
    0.89
    '
    0.86
    +
    0.86
    ,
    0.85
    -
    0.85
    1
    0.84
    Activations Density 2.652%

    No Known Activations