© 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. 242609
    Prev
    Next
    INDEX
    Explanations

    category, election, year

    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
    ancio
    0.47
     Marion
    0.46
     सुमन
    0.46
     Фе
    0.44
    </h3>
    0.44
     Tipper
    0.44
     Mirage
    0.44
     Humane
    0.44
     Eaton
    0.44
     humane
    0.44
    POSITIVE LOGITS
    ı
    0.59
    iz
    0.55
    ז
    0.54
    adikan
    0.54
    ısı
    0.52
    attham
    0.52
    ıs
    0.51
    맞
    0.49
    at
    0.48
    ά
    0.48
    Activations Density 0.000%

    No Known Activations