© 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. 255497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     fija
    0.53
    リー
    0.50
    ヴォ
    0.50
    나
    0.49
     ちゃう
    0.49
    acf
    0.49
    き
    0.49
    𝓭
    0.48
     লিপ
    0.48
     書い
    0.47
    POSITIVE LOGITS
     సర్
    0.53
     concurrent
    0.45
     Experienced
    0.44
     Concurrent
    0.43
     HIM
    0.43
     Adequate
    0.42
     permissions
    0.41
     Middleware
    0.41
     orderBy
    0.41
    ₫
    0.40
    Activations Density 0.000%

    No Known Activations