© 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. 252858
    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
    owneri
    0.70
    $\--
    0.63
    comodule
    0.61
    itabbam
    0.56
    ilization
    0.55
    socketList
    0.54
     colis
    0.54
    addPreferred
    0.54
    व्यक्ति
    0.54
     elevationMap
    0.54
    POSITIVE LOGITS
    _
    0.53
     “
    0.50
     inner
    0.49
     gar
    0.48
     Kar
    0.48
     –
    0.48
     The
    0.47
     har
    0.47
     I
    0.46
     re
    0.46
    Activations Density 0.000%

    No Known Activations