© 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. 254325
    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
    ycling
    0.54
    ா
    0.53
    ate
    0.49
     praktisch
    0.49
    .[/
    0.49
     আলো
    0.48
     számára
    0.48
    ew
    0.47
    IFE
    0.47
     devraient
    0.47
    POSITIVE LOGITS
    ради
    0.48
    ادف
    0.45
    萝卜
    0.44
    اسية
    0.43
    alus
    0.42
    тое
    0.42
    게요
    0.42
    უთ
    0.42
    불어
    0.42
    ඡ
    0.41
    Activations Density 0.000%

    No Known Activations