© 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. 4230
    Prev
    Next
    INDEX
    Explanations

    essay, story, poem, rap

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

    This neuron fires on numeric tokens (digits or numbers used in citations, page counts, years, etc.).

    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
     hinzufügen
    0.71
     orbifold
    0.70
     tiktok
    0.70
     vídeos
    0.70
     symplect
    0.70
     padx
    0.69
    ffmpeg
    0.68
    
    0.67
     emoji
    0.67
     ছবিতে
    0.67
    POSITIVE LOGITS
    Essay
    0.93
     Essays
    0.89
     Essay
    0.89
     essays
    0.81
     Dissertation
    0.78
     essay
    0.77
     eBook
    0.75
    Bald
    0.71
    Assignment
    0.71
    Culture
    0.71
    Activations Density 0.042%

    No Known Activations