© 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. 252731
    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
    ',
    0.54
    ,
    0.49
    ",
    0.46
    \
    0.43
     Four
    0.42
     Flexible
    0.42
    <
    0.40
     Half
    0.40
    үз
    0.39
    !
    0.39
    POSITIVE LOGITS
     結果
    0.51
     シュ
    0.51
     ટી
    0.50
     বাধ্যতামূলক
    0.49
    nicheskij
    0.48
     ಸೇವ
    0.48
     ಕೊಟ್ಟ
    0.48
     今
    0.48
    ಷ್
    0.48
     ಯು
    0.47
    Activations Density 0.000%

    No Known Activations