© 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. 687
    Prev
    Next
    INDEX
    Explanations

    listing or etc

    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
    asının
    0.35
    édération
    0.33
    omegranate
    0.33
    菪
    0.33
     alcoholic
    0.32
     względu
    0.31
     nutritive
    0.31
     axonal
    0.31
     homosexual
    0.30
     vasodil
    0.30
    POSITIVE LOGITS
    গুলো
    0.50
     وغیرہ
    0.41
     І
    0.39
     країни
    0.39
     وغيرها
    0.38
     тощо
    0.37
     etc
    0.36
    .
    0.36
    ।
    0.36
    ↵↵
    0.36
    Activations Density 0.434%

    No Known Activations