© 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. 17019
    Prev
    Next
    INDEX
    Explanations

    review articles

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

    review or overview

    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
    测试
    0.60
     测试
    0.56
     اختبار
    0.54
    طع
    0.54
    拒绝
    0.52
     테스트
    0.50
    ലുള്ള
    0.50
    绦
    0.50
    节日
    0.50
    同样的
    0.49
    POSITIVE LOGITS
     reviews
    0.82
     review
    0.80
    review
    0.73
     trends
    0.73
    reviewed
    0.72
     Trends
    0.69
    reviews
    0.68
     REVIEW
    0.68
     reviewed
    0.68
     technologies
    0.68
    Activations Density 0.114%

    No Known Activations