© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    authorization arguments

    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
    ಾರ್
    0.52
    वल
    0.47
    कल
    0.45
    בר
    0.43
    の一
    0.43
    Endpoints
    0.43
    یرو
    0.43
    朹
    0.43
    p
    0.42
    хай
    0.42
    POSITIVE LOGITS
     traitor
    0.46
     hurricanes
    0.46
     zł
    0.45
    JI
    0.44
     espírito
    0.44
     zl
    0.43
     pitcher
    0.42
    ，
    0.42
     ji
    0.42
     mimic
    0.42
    Activations Density 0.003%

    No Known Activations