© 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. 45702
    Prev
    Next
    INDEX
    Explanations

    call and answer

    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
    Negative Logits
     especially
    -1.31
     особенно
    -1.26
    Especially
    -1.23
     empie
    -1.20
     you
    -1.18
    太大
    -1.18
     tipo
    -1.13
     we
    -1.13
    还有
    -1.13
    我们
    -1.11
    POSITIVE LOGITS
    ebly
    1.23
    謚
    1.22
    igth
    1.17
     answer
    1.14
     about
    1.13
    されており
    1.08
    čního
    1.06
     Ді
    1.05
    がみ
    1.04
    brtc
    1.02
    Activations Density 0.087%

    No Known Activations