© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64760
    Prev
    Next
    INDEX
    Explanations

    z followed by hyphens or index

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

    The neuron fires on numeric tokens—i.e. any stand‐alone digits or numbers in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     morbidity
    -0.75
     {.
    -0.70
    Heel
    -0.68
    RequestContext
    -0.68
     蓮
    -0.66
    邹
    -0.66
     deform
    -0.64
     என்
    -0.64
     cook
    -0.63
    ţie
    -0.62
    POSITIVE LOGITS
     Padding
    0.68
     Index
    0.68
    hael
    0.67
    currentUser
    0.67
    adí
    0.66
    を起こ
    0.65
    ôr
    0.65
     index
    0.65
    let
    0.65
     дета
    0.65
    Activations Density 0.073%

    No Known Activations