© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128027
    Prev
    Next
    INDEX
    Explanations

    numbers and math expressions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cilindros
    -1.13
    FFEE
    -1.11
     regulador
    -1.07
     reservar
    -1.05
    点此
    -1.03
    colha
    -1.02
     reservado
    -0.98
    sists
    -0.97
    我們
    -0.96
    codile
    -0.95
    POSITIVE LOGITS
     +
    1.16
     for
    1.12
     of
    1.08
     -->
    1.05
     plus
    1.05
     would
    1.04
     to
    1.02
    +
    1.00
    }+
    0.96
     then
    0.94
    Activations Density 0.009%

    No Known Activations