© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25701
    Prev
    Next
    INDEX
    Explanations

    business systems and solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویتامین
    -1.95
     витами
    -1.86
    妩
    -1.77
     朝食
    -1.63
    ῖν
    -1.57
     иллюстрация
    -1.55
     cukru
    -1.52
     hábit
    -1.50
    ureusement
    -1.50
    Köszi
    -1.48
    POSITIVE LOGITS
    וּ
    2.02
    靭
    1.98
     cost
    1.87
    靱
    1.78
     system
    1.77
     solution
    1.63
     your
    1.63
     systems
    1.55
     or
    1.53
     hardware
    1.48
    Activations Density 0.110%

    No Known Activations