© 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. 10208
    Prev
    Next
    INDEX
    Explanations

    URL prefixes and punctuation

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

    errors early, defined, least

    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
    ל
    0.60
    WHAT
    0.53
    א
    0.52
    ס
    0.52
    يي
    0.47
    ِي
    0.47
     صغير
    0.47
    ז
    0.46
    يني
    0.46
    شوف
    0.45
    POSITIVE LOGITS
     ditth
    0.49
     habilidad
    0.46
     любых
    0.45
     informes
    0.45
     उर्व
    0.44
    iteiten
    0.43
     مداخل
    0.43
    un
    0.42
    avik
    0.42
     comunicaciones
    0.42
    Activations Density 0.000%

    No Known Activations