© 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. 103453
    Prev
    Next
    INDEX
    Explanations

    dates following 'on'

    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
     to
    -1.72
    丷
    -1.67
     if
    -1.66
    我们要
    -1.63
     inaugura
    -1.60
    籥
    -1.57
     you
    -1.53
     silahkan
    -1.52
    end
    -1.48
    甃
    -1.48
    POSITIVE LOGITS
     and
    1.60
    ’
    1.56
    '
    1.49
    _{
    1.41
    л
    1.39
     betrug
    1.32
    、
    1.30
     untuk
    1.30
     marvels
    1.28
     hii
    1.27
    Activations Density 0.029%

    No Known Activations