© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34797
    Prev
    Next
    INDEX
    Explanations

    criteria or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,"
    0.41
    in
    0.40
    ൻ
    0.40
    ");
    0.39
    ,”
    0.39
    ucionales
    0.38
    ב
    0.38
    лини
    0.37
    კ
    0.37
    ini
    0.37
    POSITIVE LOGITS
     rendimiento
    0.52
     performans
    0.48
     collecte
    0.47
     fonctionnalités
    0.45
     douceur
    0.45
     parámetros
    0.44
     renseignements
    0.44
     Warranty
    0.44
     Tested
    0.44
     hyperparameters
    0.43
    Activations Density 0.002%

    No Known Activations