© 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. 117363
    Prev
    Next
    INDEX
    Explanations

    from word or phrase

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

    search engines or background context

    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
    ↵↵
    0.55
    pp
    0.48
    u
    0.46
    ↵↵↵
    0.45
    nton
    0.44
     contenido
    0.43
    ods
    0.43
     ninguno
    0.42
     Bres
    0.42
     Tavares
    0.42
    POSITIVE LOGITS
    墘
    0.54
     রাখিয়া
    0.52
    庥
    0.49
     دنیا
    0.48
    ч
    0.48
    ހ
    0.46
    жли
    0.46
    ພວກເຮ
    0.45
     મો
    0.45
    ส
    0.45
    Activations Density 0.000%

    No Known Activations