© 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. 259660
    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
    ip
    0.47
    fix
    0.46
    ">${
    0.46
    elp
    0.45
    io
    0.44
    awesome
    0.44
    fit
    0.43
    l
    0.43
    гото
    0.43
    Awesome
    0.42
    POSITIVE LOGITS
     Provost
    0.46
     alem
    0.45
     অধিকার
    0.45
     aliqu
    0.45
     దీని
    0.44
    他又
    0.44
     Aux
    0.43
     بیاکتنې
    0.43
    了起来
    0.43
     Auxiliary
    0.43
    Activations Density 0.000%

    No Known Activations