© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31540
    Prev
    Next
    INDEX
    Explanations

    .net and code components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x92>
    0.40
     Capacitor
    0.39
    Информация
    0.39
     Dataset
    0.39
     интерфей
    0.38
    პ
    0.38
     Coefficients
    0.38
    доро
    0.38
    ద్
    0.37
     कॉ
    0.37
    POSITIVE LOGITS
     messo
    0.41
     nowhere
    0.39
     मांड
    0.39
     klaar
    0.38
     toho
    0.38
    把
    0.38
    っちゃ
    0.38
    grab
    0.37
     talked
    0.37
     rząd
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.