© 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. 40044
    Prev
    Next
    INDEX
    Explanations

    functions that get data

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

    The neuron fires on method or function identifiers—especially those starting with “Get”—in code snippets.

    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
    this
    -3.30
    i
    -3.00
    e
    -3.00
    All
    -2.91
    What
    -2.80
    you
    -2.75
    }
    -2.66
    how
    -2.64
    How
    -2.63
    one
    -2.58
    POSITIVE LOGITS
    tedì
    2.84
     ‘’
    2.77
     '';
    2.61
    𓇼
    2.52
     ‘‘
    2.48
    RemindMe
    2.47
    韡
    2.44
    寕
    2.34
    丌
    2.31
    ᐠ
    2.30
    Activations Density 0.001%

    No Known Activations