© 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. 50225
    Prev
    Next
    INDEX
    Explanations

    data sources and reporting

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

    training data

    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
    el
    0.66
    ﺤ
    0.59
    alı
    0.57
    erden
    0.57
    ulación
    0.55
     información
    0.54
     БД
    0.54
     ECHO
    0.53
     RAC
    0.52
    ز
    0.52
    POSITIVE LOGITS
    愎
    0.56
    拘
    0.56
     علاج
    0.55
     पर
    0.52
    만을
    0.52
     تنا
    0.52
     Located
    0.51
     tycker
    0.51
     Zijn
    0.51
     هغه
    0.51
    Activations Density 0.033%

    No Known Activations