© 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. 221793
    Prev
    Next
    INDEX
    Explanations

    Cobham, Škorpil, cities, authors

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

    Gemma team at

    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
     নির্মাণ
    0.52
    牌
    0.52
    ”（
    0.48
     নগর
    0.45
    運
    0.45
     columnar
    0.45
     lehet
    0.44
    不動
    0.44
    ала
    0.44
     külön
    0.43
    POSITIVE LOGITS
    z
    0.54
    in
    0.53
    i
    0.53
    an
    0.52
    y
    0.51
    e
    0.49
    tym
    0.49
    d
    0.48
    o
    0.48
    ऊ
    0.47
    Activations Density 0.000%

    No Known Activations