© 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. 24127
    Prev
    Next
    INDEX
    Explanations

    scrub, confess, defeat

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

    explaining word definitions and examples

    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
     类型
    0.46
     बोली
    0.40
     এতটাই
    0.40
    🍤
    0.38
    演员
    0.38
     equilíbrio
    0.38
     nhấn
    0.38
     분명
    0.38
    ຼ
    0.38
    嗯
    0.38
    POSITIVE LOGITS
     devoting
    0.46
     لقد
    0.45
     physicians
    0.44
     የ
    0.42
     Did
    0.42
     doctors
    0.41
     scanty
    0.41
     voulait
    0.41
     bylo
    0.40
     Estou
    0.40
    Activations Density 0.006%

    No Known Activations