© 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. 257293
    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
    $('
    0.52
     solitons
    0.48
     현
    0.48
    ת
    0.47
    현
    0.47
    ה
    0.47
    ນ
    0.46
    elsen
    0.46
    ulis
    0.46
    guas
    0.45
    POSITIVE LOGITS
     întâm
    0.52
     dajj
    0.48
     eccess
    0.48
     NSFW
    0.46
    椏
    0.46
     dû
    0.46
     vâr
    0.43
     داله
    0.43
    ']}
    0.42
     exces
    0.42
    Activations Density 0.000%

    No Known Activations