© 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. 3844
    Prev
    Next
    INDEX
    Explanations

    ID definitions in code

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

    This neuron detects numeric tokens (numbers and numeric-like IDs) in the text.

    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
     enzimas
    0.62
    VECTOR
    0.58
     adiab
    0.57
    abcdef
    0.57
    }[[
    0.57
    lbrack
    0.56
    Якщо
    0.56
    vVertex
    0.56
     Казіно
    0.56
    racellular
    0.56
    POSITIVE LOGITS
    :
    0.61
     :
    0.60
     inl
    0.59
     =
    0.57
    련
    0.56
     diễn
    0.55
     outweighed
    0.55
     likes
    0.54
     as
    0.54
     cheered
    0.53
    Activations Density 0.000%

    No Known Activations