© 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. 232251
    Prev
    Next
    INDEX
    Explanations

    root access and configuration

    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
    石
    0.52
    ES
    0.48
    EL
    0.45
    嚥
    0.45
     IL
    0.44
    刎
    0.44
     पहुँचा
    0.43
    angled
    0.43
    QR
    0.43
     স্পর্শ
    0.43
    POSITIVE LOGITS
     мама
    0.53
     modèle
    0.52
    те
    0.52
     salaire
    0.48
    не
    0.48
     топ
    0.46
     смартфо
    0.46
    и
    0.45
    рук
    0.45
    при
    0.44
    Activations Density 0.000%

    No Known Activations