© 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. 87551
    Prev
    Next
    INDEX
    Explanations

    separators or slashes

    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
    ydı
    0.49
     cuadr
    0.48
     sparsim
    0.47
    瀑
    0.47
    嶌
    0.47
     attraverso
    0.47
    .",[
    0.46
    োহণ
    0.46
    प्रकारे
    0.45
     ذریع
    0.45
    POSITIVE LOGITS
    ↵↵
    0.56
     insoluble
    0.52
     urgently
    0.45
     Samsung
    0.43
     launches
    0.43
     কিড
    0.42
     sectors
    0.42
     releases
    0.42
     unveils
    0.42
     MEGA
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.