© 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. 152096
    Prev
    Next
    INDEX
    Explanations

    related matter

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

    meaningful opportunities

    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
    isce
    0.46
     ಐ
    0.45
     claust
    0.44
     ഐ
    0.44
     ఐ
    0.44
     fournisseur
    0.43
    随后
    0.42
     כן
    0.42
    ेंगे
    0.41
    чего
    0.41
    POSITIVE LOGITS
    وت
    0.47
    Basketball
    0.47
    ᄍ
    0.46
    Spain
    0.44
    ウド
    0.43
     yh
    0.43
    Statistics
    0.43
    3
    0.43
     danam
    0.42
    Mt
    0.42
    Activations Density 0.001%

    No Known Activations