© 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. 138366
    Prev
    Next
    INDEX
    Explanations

    chart, indeed, sir, recording

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

    step sequence

    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
    淮
    0.47
    kä
    0.46
    겠죠
    0.46
     χρήση
    0.46
    嘴
    0.46
    スー
    0.45
     активность
    0.44
    ضغط
    0.44
    arct
    0.44
     normalen
    0.44
    POSITIVE LOGITS
     سی
    0.47
     librarians
    0.46
    鏗
    0.46
     DISTRICT
    0.45
     fisheries
    0.44
     bereavement
    0.43
     librarian
    0.43
    ोलॉजी
    0.42
    DEPARTMENT
    0.42
     dopiero
    0.42
    Activations Density 0.002%

    No Known Activations