© 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. 115336
    Prev
    Next
    INDEX
    Explanations

    nice touches

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

    action modifiers and their objects

    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
     abelian
    0.56
     Explained
    0.49
     Gleich
    0.48
    abell
    0.48
     Equations
    0.47
     petting
    0.46
    醂
    0.45
     Saison
    0.44
     incarcer
    0.44
    ı
    0.43
    POSITIVE LOGITS
    MH
    0.49
    對
    0.49
    十七
    0.48
    그
    0.48
    應用
    0.48
     splashed
    0.47
    十六
    0.47
     মেরামত
    0.47
    Kv
    0.44
    摇
    0.44
    Activations Density 0.000%

    No Known Activations