© 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. 18129
    Prev
    Next
    INDEX
    Explanations

    following instructions to set or paste

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

    html/javascript closing syntax

    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
     españoles
    0.44
    ‌هایی
    0.43
     Pinto
    0.43
     کمتر
    0.40
     फतेह
    0.40
     وب
    0.40
    *
    0.39
     Española
    0.39
     Fateh
    0.39
     مح
    0.39
    POSITIVE LOGITS
    瑪
    0.39
    ोट
    0.39
    ॉप
    0.37
    ISING
    0.37
     magnet
    0.37
    ॉड
    0.37
    Mâ
    0.36
    ೋತಿ
    0.36
     chairman
    0.36
    Исто
    0.36
    Activations Density 0.000%

    No Known Activations