© 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. 64710
    Prev
    Next
    INDEX
    Explanations

    method calls and code snippets

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

    This neuron activates on function or method declarations—i.e. return types and method names followed by parentheses in 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_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
    taient
    -1.05
    ämie
    -1.02
    teils
    -1.01
    謠
    -0.99
     Chrift
    -0.98
    שמי
    -0.97
    lijck
    -0.97
     Accessoires
    -0.96
    УДК
    -0.95
    edipus
    -0.94
    POSITIVE LOGITS
     only
    1.06
     searches
    1.04
    eloma
    0.96
     wobec
    0.95
    </h3>
    0.95
    <thead>
    0.94
     kuten
    0.92
     without
    0.90
     versions
    0.90
     such
    0.90
    Activations Density 0.004%

    No Known Activations