© 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. 1591
    Prev
    Next
    INDEX
    Explanations

    over hundreds, really HAVE, truly think

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

    sections access

    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
    א
    0.53
    따
    0.52
    같이
    0.51
    저
    0.50
    Parte
    0.49
    πο
    0.48
    톤
    0.48
    AD
    0.48
    positivo
    0.47
    军
    0.47
    POSITIVE LOGITS
     rhs
    0.47
     Idle
    0.46
     आइ
    0.45
     للح
    0.44
     тел
    0.44
    šanu
    0.44
     為
    0.44
     kol
    0.43
     jes
    0.42
     الفصل
    0.42
    Activations Density 0.000%

    No Known Activations