© 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. 22-GEMMASCOPE-RES-131K
    7. 129147
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric literals (integer or decimal constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code imports and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     المجتمع
    -0.84
    ("")]
    -0.82
    闡
    -0.79
     Charlotte
    -0.78
     Greater
    -0.78
    itatis
    -0.77
     Café
    -0.77
     Statement
    -0.77
     Cafe
    -0.76
     Jonathan
    -0.75
    POSITIVE LOGITS
     JScrollPane
    0.92
    marily
    0.86
    tuigen
    0.84
     chiusura
    0.83
     principalmente
    0.82
    édie
    0.81
    とにかく
    0.80
     Suction
    0.79
     questione
    0.79
    ʤ
    0.79
    Activations Density 0.005%

    No Known Activations