© 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. 84205
    Prev
    Next
    INDEX
    Explanations

    Columbia University

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

    This neuron activates on code tokens referring to configuration or state settings (e.g. “config”, “ModelState”, “setConfig”).

    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
     sämtliche
    -1.82
    蟥
    -1.67
     französische
    -1.62
     dasselbe
    -1.59
     entsprechende
    -1.57
     antigüedad
    -1.54
     spezielle
    -1.52
    訁
    -1.51
     vollständige
    -1.48
    with
    -1.48
    POSITIVE LOGITS
    </h4>
    1.65
     şark
    1.59
     However
    1.57
     вашем
    1.57
     eloquent
    1.55
    ･･
    1.48
    黩
    1.47
     olsa
    1.46
    (!__
    1.46
     oyuncu
    1.45
    Activations Density 0.000%

    No Known Activations