© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6413
    Prev
    Next
    INDEX
    Explanations

    listing and including categories

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

    This neuron chiefly responds to punctuation marks (especially commas and sentence-ending periods).

    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
     Deshalb
    0.80
     нередко
    0.76
     Perché
    0.75
     Когда
    0.74
    
    0.73
    だから
    0.71
     Сколько
    0.71
     Какие
    0.71
     Потому
    0.71
     Кстати
    0.71
    POSITIVE LOGITS
     (
    0.86
     curated
    0.77
     curation
    0.73
     dataset
    0.73
    0
    0.73
    0.71
     iterations
    0.70
     original
    0.70
     includes
    0.69
     contexts
    0.68
    Activations Density 1.548%

    No Known Activations