© 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. 71794
    Prev
    Next
    INDEX
    Explanations

    polynomials with exponents

    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
    跸
    -1.76
     semelh
    -1.72
    ofed
    -1.66
    鈈
    -1.63
     }}(
    -1.59
    已经在
    -1.57
    ĭ
    -1.54
    ated
    -1.52
     cuándo
    -1.52
     ライト
    -1.51
    POSITIVE LOGITS
    8
    2.50
    3
    1.88
    7
    1.84
    6
    1.75
    2
    1.68
    '
    1.67
     его
    1.61
     it
    1.54
     first
    1.52
    4
    1.52
    Activations Density 0.032%

    No Known Activations