© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    command-line arguments flags

    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
     podrían
    0.42
    蝰
    0.41
    裵
    0.41
     但
    0.40
     уважаемые
    0.40
    AppBsky
    0.40
    劝
    0.40
    goài
    0.39
    美好
    0.39
     समझौ
    0.38
    POSITIVE LOGITS
     ${
    0.44
    7
    0.44
    ,”
    0.44
    ”;
    0.44
     ('
    0.41
    *
    0.41
    p
    0.41
    ,"
    0.41
     (“
    0.40
     denotes
    0.40
    Activations Density 0.043%

    No Known Activations