© 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. 238531
    Prev
    Next
    INDEX
    Explanations

    non-life threatening

    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
    ."[
    0.50
    tä
    0.50
    a
    0.50
    i
    0.47
    breaks
    0.46
    in
    0.44
    snapshots
    0.44
    masks
    0.44
    िवे
    0.44
    attacks
    0.43
    POSITIVE LOGITS
     Fraction
    0.49
     ವಿಧಾನಸ
    0.46
     Оста
    0.45
    但是我
    0.45
    ﺤ
    0.44
     لك
    0.44
    老公
    0.44
    ودي
    0.44
    ﻤ
    0.43
    銠
    0.43
    Activations Density 0.000%

    No Known Activations