© 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. 116646
    Prev
    Next
    INDEX
    Explanations

    true dub

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

    positive slant for thesis scope

    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
     へ
    0.56
     bhij
    0.54
    ısının
    0.53
     リボン
    0.52
    Databaze
    0.51
    บริเวณ
    0.51
     り
    0.50
     puriso
    0.50
     മുഴുവ
    0.50
     ボディ
    0.50
    POSITIVE LOGITS
    م
    0.49
    https
    0.47
    مث
    0.46
    فع
    0.45
     Miss
    0.45
    Miss
    0.44
     Board
    0.42
     Wheat
    0.41
    Wheat
    0.41
     fath
    0.41
    Activations Density 0.000%

    No Known Activations