© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166137
    Prev
    Next
    INDEX
    Explanations

    first draft

    np_acts-logits-general · gemini-2.5-flash-lite

    understandings and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     チェック
    0.49
    আমিন
    0.48
     उछ
    0.47
    nSamples
    0.46
     八
    0.45
     关闭
    0.45
    uasion
    0.44
    맇
    0.44
    rosophila
    0.44
     роста
    0.44
    POSITIVE LOGITS
     monolithic
    0.52
    es
    0.50
    é
    0.49
     Decker
    0.48
     continuous
    0.47
     Lander
    0.47
     typewriter
    0.46
    ca
    0.46
     handler
    0.46
     libre
    0.46
    Activations Density 0.000%

    No Known Activations