© 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. 228420
    Prev
    Next
    INDEX
    Explanations

    employment law and corporate teams

    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
     wy
    0.46
     prawie
    0.46
     stopni
    0.46
     zg
    0.46
    2
    0.46
     million
    0.45
    ха
    0.45
     Goshen
    0.44
     zez
    0.43
     vy
    0.43
    POSITIVE LOGITS
    asal
    0.65
    Texts
    0.53
    --");
    0.49
    Italie
    0.48
    omanian
    0.47
    evaluated
    0.47
     ۔
    0.47
    versible
    0.47
    Sidebar
    0.46
    म्प्ट
    0.46
    Activations Density 0.000%

    No Known Activations