© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40033
    Prev
    Next
    INDEX
    Explanations

    Swift code

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

    The neuron activates on numeric literal tokens (i.e. numbers in code or text).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     rése
    -1.95
    
    -1.83
    漚
    -1.82
    ଃ
    -1.81
    erdere
    -1.73
    醅
    -1.70
    
    -1.70
    ఽ
    -1.67
    婓
    -1.67
     bluz
    -1.65
    POSITIVE LOGITS
    "
    2.09
     if
    1.95
     of
    1.76
     after
    1.69
     at
    1.66
     from
    1.58
    ;
    1.55
    :
    1.52
    9
    1.48
     while
    1.44
    Activations Density 0.006%

    No Known Activations