© 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. 227690
    Prev
    Next
    INDEX
    Explanations

    eat plant-based, default view, pollsters, skills, either, force, pre-loaded

    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
    我
    0.48
    烦
    0.48
     dép
    0.46
     bachelor
    0.46
     നമു
    0.46
     règne
    0.45
     bacterium
    0.44
    న్నీ
    0.44
     vise
    0.43
    感
    0.43
    POSITIVE LOGITS
     Wholesale
    0.46
     wholesalers
    0.46
     Dioxide
    0.46
    rimidin
    0.44
     Federal
    0.43
     wholesale
    0.43
    wholesale
    0.43
    ormous
    0.43
    ductory
    0.42
    preferences
    0.41
    Activations Density 0.001%

    No Known Activations