© 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. 141927
    Prev
    Next
    INDEX
    Explanations

    grant to, preparation to, out of, leave the

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

    make coordinated

    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
    िया
    0.52
    us
    0.49
    র্
    0.45
     аўтаматы
    0.45
    ä
    0.45
    och
    0.45
    icles
    0.44
    ानी
    0.44
    益
    0.44
    ings
    0.43
    POSITIVE LOGITS
     centrale
    0.48
    خد
    0.48
    هان
    0.45
     dictator
    0.45
    KV
    0.45
     parola
    0.44
     bays
    0.44
    KW
    0.44
    ۰۰
    0.44
    TARIFF
    0.44
    Activations Density 0.000%

    No Known Activations