© 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. 8307
    Prev
    Next
    INDEX
    Explanations

    comments, code execution, or separators

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

    multiple languages and code

    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
     educa
    0.41
     educación
    0.39
     nourriture
    0.39
     baths
    0.39
    a
    0.39
    YLE
    0.38
    ITIS
    0.38
    education
    0.38
     éduc
    0.38
    parachute
    0.38
    POSITIVE LOGITS
     또는
    0.37
    };
    0.37
    或
    0.35
    0.35
    0.34
     상태
    0.33
    ᅪ
    0.31
     clearContext
    0.31
     অথবা
    0.30
     Ваш
    0.30
    Activations Density 0.000%

    No Known Activations