© 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. 64683
    Prev
    Next
    INDEX
    Explanations

    foreign language multi-script

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

    West, Winston, locations

    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
     ۸
    0.46
    0.46
     Zimmerman
    0.45
     %
    0.43
     rand
    0.43
     ctrl
    0.42
     m
    0.42
     stock
    0.42
     Rank
    0.42
     ২
    0.42
    POSITIVE LOGITS
    Caf
    0.56
    𝗰
    0.52
     מלא
    0.51
     cilia
    0.50
    fireFlower
    0.49
    सिव
    0.47
     права
    0.47
     alienation
    0.46
    䡓
    0.46
    Cafe
    0.46
    Activations Density 0.000%

    No Known Activations