© 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. 254129
    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
     ys
    0.54
     navegación
    0.50
     navig
    0.47
     nevo
    0.47
     navigator
    0.47
     <=
    0.45
     achats
    0.44
     স্তর
    0.44
     brigade
    0.43
    <0xBC>
    0.43
    POSITIVE LOGITS
    НК
    0.49
     ക്രിക്ക
    0.49
    ′,
    0.45
    کرد
    0.44
    Ⲛ
    0.44
    ट्यूब
    0.44
    рел
    0.44
    РС
    0.44
    ^{*}(\
    0.44
    bills
    0.43
    Activations Density 0.000%

    No Known Activations