© 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. 229126
    Prev
    Next
    INDEX
    Explanations

    steps, stages, or lists

    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
     результатов
    0.55
     záz
    0.47
     Results
    0.46
    烜
    0.46
     Ahora
    0.45
     símbolos
    0.45
     BuildConfig
    0.44
     પહેલા
    0.44
     doenças
    0.44
     restricciones
    0.44
    POSITIVE LOGITS
    ↵↵
    0.55
    on
    0.48
     confided
    0.45
     conn
    0.45
    os
    0.44
     cowardly
    0.44
     reckons
    0.44
    *,
    0.43
    elle
    0.42
     cak
    0.42
    Activations Density 0.000%

    No Known Activations