© 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. 173445
    Prev
    Next
    INDEX
    Explanations

    common phrases and continuations

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

    optimizing and completing descriptions

    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
    ריך
    0.50
    Separ
    0.45
    anlı
    0.43
    ərbaycan
    0.42
    Worst
    0.42
    Determin
    0.42
    赵
    0.42
    Feder
    0.42
    Hosted
    0.40
    Generic
    0.40
    POSITIVE LOGITS
    َه
    0.55
     besondere
    0.50
     locker
    0.49
     ショルダー
    0.47
     Jackets
    0.47
     invariable
    0.46
     Morn
    0.46
     by
    0.46
    ation
    0.45
     proti
    0.45
    Activations Density 0.001%

    No Known Activations