© 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. 114657
    Prev
    Next
    INDEX
    Explanations

    plotting, harvested, collection, executives

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

    advance reservations and printing

    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
    坸
    0.54
    larla
    0.52
     avulla
    0.52
    ūn
    0.52
     desech
    0.50
    rofoam
    0.49
    untamiento
    0.48
    abbam
    0.48
     verme
    0.48
     legenda
    0.47
    POSITIVE LOGITS
     dipped
    0.45
    )$,
    0.43
    anet
    0.41
    年
    0.41
     (\$
    0.41
     inked
    0.41
    യാ
    0.40
    spoken
    0.40
    ните
    0.39
    empirical
    0.39
    Activations Density 0.000%

    No Known Activations