© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13281
    Prev
    Next
    INDEX
    Explanations

    ServiceStack, ServiceMix, service/

    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_10/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
    ientras
    -3.38
    橛
    -3.28
    鬭
    -3.03
     fabriqué
    -2.91
    鲧
    -2.86
    釤
    -2.69
     westfalen
    -2.67
    戕
    -2.66
     they
    -2.64
    
    -2.61
    POSITIVE LOGITS
    This
    4.06
    However
    3.92
    These
    3.83
    There
    3.64
    Although
    3.56
    With
    3.27
    Since
    3.23
    While
    3.14
    What
    3.13
    Also
    3.09
    Activations Density 0.050%

    No Known Activations