© 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. 13635
    Prev
    Next
    INDEX
    Explanations

    code structures and programming concepts

    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
    няются
    0.38
    ђ
    0.37
    ummer
    0.36
    promises
    0.36
    ложи
    0.35
    一群
    0.35
     போதும்
    0.34
    umb
    0.34
     posibil
    0.33
    给你
    0.33
    POSITIVE LOGITS
    Roi
    0.39
    វិ
    0.39
     नसल्या
    0.39
     pouvait
    0.39
    Torpedo
    0.39
     bytecode
    0.38
    媧
    0.38
     Proxy
    0.38
    Crop
    0.38
    Map
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.