© 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. 64544
    Prev
    Next
    INDEX
    Explanations

    end of year dates

    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
    ݯ
    -1.37
     trám
    -1.33
     tomto
    -1.32
    あー
    -1.22
    }$.
    -1.21
     emisiones
    -1.21
    あぁ
    -1.17
    )}{
    -1.17
     También
    -1.16
     Queue
    -1.14
    POSITIVE LOGITS
    '
    1.38
    風景
    1.23
     what
    1.16
    だが
    1.16
     annually
    1.13
    景色
    1.13
     could
    1.11
     of
    1.10
    があるので
    1.09
     every
    1.07
    Activations Density 0.030%

    No Known Activations