© 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. 68522
    Prev
    Next
    INDEX
    Explanations

    zero value measurements

    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
     و
    -1.49
    ad
    -1.46
    ot
    -1.41
    not
    -1.40
     inaprop
    -1.39
     рынке
    -1.37
    ans
    -1.34
     verkligen
    -1.34
    satunya
    -1.32
    va
    -1.30
    POSITIVE LOGITS
    There
    1.47
     for
    1.44
     there
    1.39
    libat
    1.36
    borsa
    1.33
    Both
    1.32
     ursprüng
    1.32
     gelungen
    1.29
     since
    1.27
    Because
    1.27
    Activations Density 0.044%

    No Known Activations