© 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. 6366
    Prev
    Next
    INDEX
    Explanations

    HTML, CSS, or JavaScript

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

    The neuron is looking for unusually long or multi‐character tokens (i.e. long words or complex tokens).

    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
     duelo
    0.64
     ennemis
    0.63
     moisturizer
    0.63
     arrondie
    0.63
     kvůli
    0.63
    戕
    0.63
     andRow
    0.63
     worsen
    0.62
     leche
    0.61
     curd
    0.61
    POSITIVE LOGITS
    又は
    0.78
    あるいは
    0.76
     will
    0.73
    ０
    0.67
     ০
    0.66
    approximately
    0.66
    することができます
    0.66
     useful
    0.65
    DanhMucSP
    0.65
     approximately
    0.64
    Activations Density 0.546%

    No Known Activations