© 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. 60611
    Prev
    Next
    INDEX
    Explanations

    and followed by various words

    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
     allows
    -1.70
     then
    -1.66
     usually
    -1.63
     almost
    -1.58
     goes
    -1.56
     continues
    -1.55
     probably
    -1.54
     [
    -1.53
     on
    -1.53
    on
    -1.52
    POSITIVE LOGITS
     gogh
    1.84
    rimos
    1.72
     raiſ
    1.70
    ឵
    1.67
     nage
    1.67
    衲
    1.67
    籴
    1.65
    StructEnd
    1.63
    фю
    1.62
    enziali
    1.61
    Activations Density 0.121%

    No Known Activations