© 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. 34-GEMMASCOPE-RES-131K
    7. 57705
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls

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

    The neuron fires on code identifiers—especially function, class or other names that start with a capital letter.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Sebelum
    -0.93
     genaue
    -0.92
     Masalah
    -0.86
     Derfor
    -0.86
     neither
    -0.86
     Ternyata
    -0.85
     mầm
    -0.85
    istical
    -0.84
    ләр
    -0.83
     Væ
    -0.83
    POSITIVE LOGITS
    void
    0.91
    ()
    0.90
    ()
    0.88
     Farbe
    0.85
     ()
    0.84
     pap
    0.83
    Why
    0.82
     geha
    0.80
    ())).
    0.79
     enkelt
    0.78
    Activations Density 0.002%

    No Known Activations