© 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. 138935
    Prev
    Next
    INDEX
    Explanations

    luger competitor

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

    code and data structures

    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
    コーヒー
    0.54
     فلس
    0.50
     آمریکا
    0.50
     커피
    0.49
    າ
    0.49
     flooded
    0.48
     attached
    0.48
     philosopher
    0.48
     اروپا
    0.47
     filozof
    0.47
    POSITIVE LOGITS
    typedef
    0.52
    ὀ
    0.48
    тего
    0.46
    typed
    0.44
     Typed
    0.44
    getenv
    0.43
    ђа
    0.43
    ուս
    0.43
    തേ
    0.43
    πά
    0.43
    Activations Density 0.002%

    No Known Activations