© 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. 55755
    Prev
    Next
    INDEX
    Explanations

    security services

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

    research reproducibility

    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
    Returning
    0.45
    ↵
    0.43
     Amateur
    0.43
     Release
    0.42
     Velocity
    0.42
     Disabled
    0.41
     Yield
    0.41
     Update
    0.40
     Transform
    0.40
     E
    0.40
    POSITIVE LOGITS
     accuses
    0.56
    マル
    0.54
    두
    0.51
    ûr
    0.50
     accuse
    0.49
     insidious
    0.49
     allege
    0.48
     consequatur
    0.48
     tumeurs
    0.48
    atás
    0.48
    Activations Density 0.000%

    No Known Activations