© 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. 42859
    Prev
    Next
    INDEX
    Explanations

    Star Wars Jedi

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

    file type

    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
    abandon
    0.49
    police
    0.47
    ÂN
    0.46
    м
    0.45
     subdue
    0.43
     כדי
    0.43
    מח
    0.42
    ม
    0.42
    を描
    0.42
     നേര
    0.41
    POSITIVE LOGITS
     Sesame
    0.47
     Esa
    0.47
     Espresso
    0.46
     Clipper
    0.46
     Mysore
    0.46
     azon
    0.44
     Sesam
    0.44
     amide
    0.43
     чуть
    0.43
     Cheryl
    0.42
    Activations Density 0.000%

    No Known Activations