© 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. 22674
    Prev
    Next
    INDEX
    Explanations

    managing the chaos

    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
    n
    -2.59
     What
    -2.39
    ться
    -2.36
     größten
    -2.30
     Why
    -2.27
     We
    -2.23
    ING
    -2.16
     on
    -2.14
    D
    -2.11
     但
    -2.09
    POSITIVE LOGITS
    嫪
    2.38
    鹇
    2.34
    ꦠ
    2.25
    璈
    2.23
     sentiers
    2.20
    猹
    2.17
    峁
    2.13
    就去
    2.13
    罽
    2.13
    Vogue
    2.09
    Activations Density 0.000%

    No Known Activations