© 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. 1390
    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
    .
    0.57
    5
    0.56
    ↵
    0.49
     package
    0.49
     buggy
    0.49
    =
    0.48
     lo
    0.48
    1
    0.48
    -
    0.48
    ...
    0.47
    POSITIVE LOGITS
     તરી
    0.66
     мүмк
    0.63
     архіви
    0.56
     Elektrokhimiya
    0.54
    StarService
    0.52
     זי
    0.52
    ಭವ
    0.52
     OBJECTTYPE
    0.51
     testaceis
    0.50
    ಗೊಂಡ
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.