© 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. 253488
    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
    🦜
    0.49
    💂
    0.48
     APA
    0.47
    ojan
    0.42
    থর
    0.42
    esercizio
    0.42
    avacanam
    0.42
    PlistBuddy
    0.42
    硖
    0.42
     FORD
    0.42
    POSITIVE LOGITS
     anime
    1.10
     Anime
    1.03
     manga
    1.01
    anime
    0.94
    Anime
    0.93
     mangas
    0.83
    漫畫
    0.81
     Manga
    0.79
    漫画
    0.77
    动漫
    0.76
    Activations Density 0.075%

    No Known Activations