© 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. 73628
    Prev
    Next
    INDEX
    Explanations

    code block syntax

    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
     thier
    -1.70
    Struktur
    -1.66
     cuire
    -1.63
     bringe
    -1.62
    皝
    -1.58
     verminder
    -1.57
    ┠
    -1.57
     karier
    -1.53
     cuisson
    -1.52
    烀
    -1.52
    POSITIVE LOGITS
    There
    1.82
     very
    1.80
    }{
    1.76
    It
    1.73
     will
    1.73
     to
    1.73
     more
    1.71
     other
    1.70
    ’
    1.69
    You
    1.67
    Activations Density 0.023%

    No Known Activations