© 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. 22-GEMMASCOPE-RES-131K
    7. 73768
    Prev
    Next
    INDEX
    Explanations

    seeking or requesting information

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    );
    -2.56
     喜欢
    -2.45
    </b>
    -2.44
    N
    -2.34
    A
    -2.34
     say
    -2.34
     startling
    -2.34
    2
    -2.30
     myriad
    -2.16
     shrewd
    -2.16
    POSITIVE LOGITS
    ments
    2.84
    .
    2.50
    啬
    2.41
    麈
    2.39
    mouthed
    2.33
    medriver
    2.30
     and
    2.22
    鶿
    2.14
    sellers
    2.13
    thodox
    2.11
    Activations Density 0.004%

    No Known Activations