© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248955
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    0.48
    ח
    0.48
    ation
    0.48
    Evaluation
    0.47
    hesion
    0.47
    Н
    0.46
    odesmium
    0.45
    Aprend
    0.45
    lo
    0.45
    Ги
    0.45
    POSITIVE LOGITS
     편
    0.50
     sécr
    0.46
     전투
    0.46
    <unused2141>
    0.45
     rápidos
    0.44
    いです
    0.43
     {'
    0.43
    バード
    0.42
    ಿಸುತ್ತದೆ
    0.42
     빠
    0.41
    Activations Density 0.004%

    No Known Activations