© 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. 211248
    Prev
    Next
    INDEX
    Explanations

    tax or joseph or readings

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

    flower, top, copies, hear, hidden, leak

    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
    鯢
    0.52
     থামাতে
    0.49
     মেরে
    0.44
    苖
    0.44
    ઓના
    0.43
     ৪৯
    0.43
    制造商
    0.43
     জলাবদ্ধ
    0.43
    新規
    0.43
    >∞</
    0.43
    POSITIVE LOGITS
     하며
    0.48
    ḧ
    0.47
     confid
    0.46
     ści
    0.45
     pierwsze
    0.45
     ساتھ
    0.44
     alongside
    0.44
     시절
    0.44
     pierwszym
    0.44
     Zeitung
    0.44
    Activations Density 0.002%

    No Known Activations