© 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. 181502
    Prev
    Next
    INDEX
    Explanations

    announcements, legal, fashion, financial ratings

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     lze
    0.52
     odk
    0.52
     hee
    0.51
     ček
    0.50
     odm
    0.49
     a
    0.47
     recense
    0.47
     cun
    0.46
     oth
    0.46
     ortodox
    0.46
    POSITIVE LOGITS
    ۸
    0.54
    ış
    0.51
    ۹
    0.50
    να
    0.50
    зываем
    0.49
     پروفیسر
    0.47
    fa
    0.47
     प्यारी
    0.47
    fns
    0.46
    natures
    0.46
    Activations Density 0.000%

    No Known Activations