© 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. 85706
    Prev
    Next
    INDEX
    Explanations

    CSS units, `px`

    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
     it
    -2.11
    '
    -1.92
     each
    -1.70
     of
    -1.61
    for
    -1.57
     Its
    -1.51
    It
    -1.50
    把它
    -1.46
     these
    -1.45
    尤其
    -1.45
    POSITIVE LOGITS
    cún
    1.63
     anoche
    1.62
    我們
    1.54
     ciebie
    1.48
    zydent
    1.46
    ktionen
    1.45
     Ciebie
    1.45
    льному
    1.45
     :—
    1.44
    猙
    1.43
    Activations Density 0.015%

    No Known Activations