© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 193742
    Prev
    Next
    INDEX
    Explanations

    foreign or specific terms

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

    ignoring the, avoid eye, determine what

    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
    j
    0.49
    p
    0.49
    <
    0.49
    as
    0.49
    x
    0.48
    <em>
    0.47
    =>{
    0.47
    はこちら
    0.46
    k
    0.46
     most
    0.45
    POSITIVE LOGITS
    пикир
    0.54
     salwar
    0.53
    เชสเตอร์
    0.52
     ആക്രമ
    0.50
     சர்
    0.49
     amarelo
    0.49
    놈
    0.49
     денег
    0.48
     الألم
    0.48
    никах
    0.48
    Activations Density 0.001%

    No Known Activations