© 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. 59255
    Prev
    Next
    INDEX
    Explanations

    interface definitions and generic types

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

    The neuron is highly sensitive to the “for” keyword (e.g. in `impl … for …`) appearing 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_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
    薆
    -1.52
     IOWA
    -1.45
     dritte
    -1.45
    癭
    -1.41
     traditionelle
    -1.38
     fragte
    -1.37
     AMERIC
    -1.37
     CHINESE
    -1.34
     SPAIN
    -1.34
    简洁
    -1.34
    POSITIVE LOGITS
     that
    1.71
    0
    1.66
     to
    1.61
     Aussehen
    1.53
    there
    1.45
     in
    1.44
    atement
    1.41
     őket
    1.41
    光是
    1.40
     seznam
    1.39
    Activations Density 0.001%

    No Known Activations