© 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. 10-GEMMASCOPE-RES-131K
    7. 85296
    Prev
    Next
    INDEX
    Explanations

    average followed by noun

    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
     vijf
    -1.69
     แต่
    -1.66
     suministros
    -1.63
     dando
    -1.59
     ランプ
    -1.58
    댔
    -1.57
     tracción
    -1.57
     usando
    -1.56
     automóviles
    -1.56
     ไม่
    -1.54
    POSITIVE LOGITS
    "
    1.95
    новение
    1.93
     people
    1.76
    Even
    1.74
     you
    1.68
    While
    1.66
    Хотя
    1.65
    ',
    1.61
     '';
    1.59
     beserta
    1.59
    Activations Density 0.016%

    No Known Activations