© 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. 146104
    Prev
    Next
    INDEX
    Explanations

    serving with tortillas

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

    SQL commands and parameters

    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
    et
    0.56
    u
    0.53
    이지
    0.52
    z
    0.51
    ש
    0.51
    দ
    0.48
    SizeMode
    0.47
    os
    0.47
    red
    0.46
    tain
    0.46
    POSITIVE LOGITS
    ﮗ
    0.52
     Ohr
    0.44
     consequent
    0.44
     escudo
    0.42
     проводи
    0.42
     ラック
    0.42
     Bisch
    0.41
     Kriegs
    0.41
     equipe
    0.41
     sultry
    0.41
    Activations Density 0.000%

    No Known Activations