© 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. 86133
    Prev
    Next
    INDEX
    Explanations

    seat belt protection

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

    growth, use, supply

    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
    ColumnKind
    0.48
     चाहिँ
    0.48
    ungkinan
    0.46
    мб
    0.46
     تمامی
    0.45
     chevaux
    0.44
     ዝ
    0.44
    ῇ
    0.43
     лицом
    0.43
     רא
    0.43
    POSITIVE LOGITS
    卧室
    0.46
     thăm
    0.44
     PROTECTION
    0.43
    H
    0.43
     proteger
    0.43
    Asia
    0.43
    Y
    0.43
    L
    0.42
     lured
    0.41
     acres
    0.41
    Activations Density 0.000%

    No Known Activations