© 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. 160367
    Prev
    Next
    INDEX
    Explanations

    ecumenism, body, benefits

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

    svg viewBox attribute

    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
    waj
    0.49
    軌
    0.49
     reflexión
    0.47
     musical
    0.45
    的方向
    0.45
     izvr
    0.44
     flying
    0.44
    wink
    0.44
    та
    0.43
     jean
    0.43
    POSITIVE LOGITS
     化学
    0.53
     Medicine
    0.50
    ERROR
    0.50
    💊
    0.49
     BENEFITS
    0.48
     சிலை
    0.48
     प्रशंसा
    0.48
     αποτέ
    0.48
    ENSION
    0.48
     اکثریت
    0.48
    Activations Density 0.000%

    No Known Activations