© 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. 258579
    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
    𠃍
    0.49
    াজ
    0.48
    ופי
    0.46
     совокуп
    0.46
     notches
    0.44
    й
    0.44
    ции
    0.43
    Moved
    0.43
    テナンス
    0.43
    Stacked
    0.43
    POSITIVE LOGITS
     sightseeing
    0.48
     Minor
    0.47
     Ling
    0.47
     beaker
    0.47
     iii
    0.47
    when
    0.45
     日
    0.45
     cataract
    0.44
     Linda
    0.43
     We
    0.42
    Activations Density 0.000%

    No Known Activations