© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113954
    Prev
    Next
    INDEX
    Explanations

    during an event or period

    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
    0
    -1.45
     who
    -1.44
     by
    -1.43
     should
    -1.34
    8
    -1.24
    應該是
    -1.23
    않
    -1.20
    9
    -1.17
    [\
    -1.17
    AS
    -1.17
    POSITIVE LOGITS
    -|-
    1.59
    𓍊
    1.34
    lético
    1.28
    になるので
    1.27
    mbolic
    1.27
     estekak
    1.27
     annual
    1.25
    fand
    1.25
    istiwa
    1.24
    bufio
    1.24
    Activations Density 0.278%

    No Known Activations