© 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. 195761
    Prev
    Next
    INDEX
    Explanations

    initialization protection requests greetings

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

    descriptive words or roles

    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
     Вул
    0.60
     rectas
    0.55
    跇
    0.54
     portas
    0.54
     HYDRO
    0.52
     канторы
    0.52
    聰
    0.50
     modelli
    0.50
     হাইড্রোক
    0.49
    ឫ
    0.49
    POSITIVE LOGITS
    ali
    0.52
    ุล
    0.47
    Number
    0.46
    abolic
    0.45
    istencia
    0.43
    ็
    0.43
     colspan
    0.42
    ing
    0.42
    اصمة
    0.41
    árs
    0.41
    Activations Density 0.000%

    No Known Activations