© 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. 196131
    Prev
    Next
    INDEX
    Explanations

    arranged marriage

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

    little bit of

    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
    ghijklmnopqrst
    0.53
    G
    0.48
     lineWidth
    0.46
    M
    0.46
    owners
    0.46
    drying
    0.45
     Better
    0.45
     Pointer
    0.45
    filtration
    0.44
     Moisture
    0.43
    POSITIVE LOGITS
     หน
    0.52
     キ
    0.52
    igné
    0.51
    ur
    0.50
     フランス
    0.50
    ið
    0.50
     couverts
    0.50
    renzia
    0.49
     特許
    0.48
     アク
    0.48
    Activations Density 0.000%

    No Known Activations