© 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. 237733
    Prev
    Next
    INDEX
    Explanations

    bathroom fan

    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
    ப்புற
    0.48
    ப்போ
    0.48
    <unused671>
    0.47
    פר
    0.46
    🥂
    0.46
    yp
    0.46
    ।
    0.46
    𝓌
    0.46
    iona
    0.46
    hift
    0.45
    POSITIVE LOGITS
     মেরামত
    0.51
     Verlust
    0.49
     Krone
    0.48
     Kluwer
    0.47
     ramos
    0.47
     erinn
    0.47
     Versch
    0.46
     Wirkung
    0.46
     Studien
    0.46
     Snell
    0.46
    Activations Density 0.001%

    No Known Activations