© 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. 180764
    Prev
    Next
    INDEX
    Explanations

    Chrome issues

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

    Jujutsu Kaisen

    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
     gerade
    0.49
    زال
    0.49
     I
    0.47
    itz
    0.47
     plains
    0.47
    ip
    0.46
    uld
    0.46
    ker
    0.45
    bild
    0.45
    lein
    0.45
    POSITIVE LOGITS
     ойношот
    0.54
    ทีม
    0.48
     Astrophysical
    0.48
    durationType
    0.47
    ◘
    0.47
    COOH
    0.47
    attho
    0.47
     COND
    0.47
     prosecutions
    0.47
    QTTR
    0.47
    Activations Density 0.000%

    No Known Activations