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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8080
    Prev
    Next
    INDEX
    Explanations

    reStructuredText (Rst) syntax

    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_all/layer_41_width_262k_l0_big
    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
    ാൻ
    0.46
     شان
    0.46
    ្នុង
    0.41
     ছ
    0.39
     شهر
    0.39
    ShaderType
    0.39
     мощности
    0.38
    策
    0.38
     ش
    0.38
     الش
    0.37
    POSITIVE LOGITS
    point
    0.66
     point
    0.63
     Point
    0.59
    aut
    0.56
    점에
    0.52
    点
    0.51
    Point
    0.50
     autod
    0.50
    點
    0.50
     autob
    0.49
    Activations Density 0.001%

    No Known Activations