© 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. 186383
    Prev
    Next
    INDEX
    Explanations

    weekend holidays

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

    areas, risks, aspirations, fractal, comprehensive

    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
    戽
    0.54
    alas
    0.51
    籿
    0.47
    osex
    0.47
    幷
    0.46
     پیچ
    0.46
    ंत्रिक
    0.44
    olefin
    0.44
    舒适
    0.44
     प्रतिबंध
    0.44
    POSITIVE LOGITS
     Up
    0.48
     Sauce
    0.48
     Ori
    0.46
     toDo
    0.46
     Leader
    0.45
     S
    0.45
     Tod
    0.44
     Saud
    0.44
     GEN
    0.44
     Luna
    0.44
    Activations Density 0.000%

    No Known Activations