© 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-65K
    7. 13262
    Prev
    Next
    INDEX
    Explanations

    code blocks and language identifiers

    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_65k_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
    in
    0.49
    č
    0.45
    ut
    0.45
    ít
    0.43
     Marijuana
    0.43
     is
    0.43
     What
    0.43
     TF
    0.43
    alu
    0.42
    insk
    0.42
    POSITIVE LOGITS
    Bolt
    0.49
    ность
    0.45
    ностей
    0.44
    Ⲏ
    0.44
    ETTE
    0.43
    Ble
    0.42
    RatingDiff
    0.41
    BLE
    0.41
     lành
    0.41
    ঵
    0.40
    Activations Density 0.058%

    No Known Activations