© 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. 195867
    Prev
    Next
    INDEX
    Explanations

    web url extensions and query parameters

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

    web urls with file extensions

    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
    reich
    0.54
     ideale
    0.53
    ka
    0.50
    berg
    0.49
    ı
    0.47
    et
    0.46
     €,
    0.46
    ole
    0.45
    ca
    0.45
    igan
    0.45
    POSITIVE LOGITS
    Marketing
    0.47
     Marketing
    0.46
     అస
    0.46
    FreeBuf
    0.46
    AGER
    0.44
    PREFIX
    0.42
    原文
    0.42
     로그인
    0.42
    SECURITY
    0.42
    語
    0.42
    Activations Density 0.001%

    No Known Activations