© 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. 25976
    Prev
    Next
    INDEX
    Explanations

    citation identifiers like pone

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

    This neuron spotlights standalone identifier-like tokens—names of modules, classes, imports, section or file labels, and other code/metadata identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     吐
    -0.87
    kowym
    -0.84
     operação
    -0.83
    legel
    -0.82
    atero
    -0.81
     هناك
    -0.81
     ír
    -0.80
    кової
    -0.80
     hjemmeside
    -0.80
    ген
    -0.79
    POSITIVE LOGITS
     and
    1.05
     or
    0.87
    今後の
    0.85
     Other
    0.84
    álat
    0.83
     OTHER
    0.79
     अन्य
    0.79
    Aplica
    0.79
     preachers
    0.76
    aperto
    0.76
    Activations Density 0.036%

    No Known Activations