© 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. 109391
    Prev
    Next
    INDEX
    Explanations

    allows students

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

    caveats and conditional actions

    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
    ُ
    0.57
    Cond
    0.56
    сть
    0.49
    经典的
    0.49
    ز
    0.49
    毓
    0.48
    DUCTION
    0.48
    遊戲
    0.48
    经典
    0.47
    ్యూ
    0.47
    POSITIVE LOGITS
    o
    0.72
     iri
    0.55
     astral
    0.54
    a
    0.54
     namam
    0.52
    an
    0.51
     erat
    0.51
    ,/
    0.50
    did
    0.50
     ra
    0.50
    Activations Density 0.000%

    No Known Activations