© 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. 134064
    Prev
    Next
    INDEX
    Explanations

    python script entry point

    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
     প্রদত্ত
    0.44
     +-
    0.41
     +,
    0.40
     เด็ก
    0.40
     defaults
    0.39
     Praise
    0.39
     paralysie
    0.38
     +.
    0.38
     keep
    0.38
     Keep
    0.38
    POSITIVE LOGITS
    urrection
    0.48
    Qin
    0.44
    ני
    0.43
    멱
    0.41
    readystate
    0.41
    ColorLegend
    0.41
     Vereinigten
    0.40
    stituting
    0.40
    ֹ
    0.40
    ractable
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.