© 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. 100489
    Prev
    Next
    INDEX
    Explanations

    LaTeX document class declaration

    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
    ’
    0.53
    .»
    0.51
    .
    0.49
    .”
    0.47
    .\"
    0.47
     使っ
    0.45
    !
    0.43
    壁
    0.43
    ación
    0.43
     đợi
    0.43
    POSITIVE LOGITS
    棻
    0.49
     Matemat
    0.49
     Byzant
    0.49
     高校
    0.49
    وكان
    0.48
     أساس
    0.47
    Alternatives
    0.47
    WithError
    0.46
    媑
    0.46
     السنوات
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.