© 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. 113881
    Prev
    Next
    INDEX
    Explanations

    coming of age

    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
    Not in Any Lists

    No Comments

    Negative Logits
    joyed
    -1.75
     iesp
    -1.52
     convencional
    -1.45
    -...
    -1.43
     »)
    -1.41
     fahrrad
    -1.41
     to
    -1.41
    內的
    -1.40
     is
    -1.39
     huwa
    -1.38
    POSITIVE LOGITS
    臯
    1.73
    原材料
    1.56
    </em>
    1.53
     a
    1.45
     кабе
    1.45
    ”
    1.44
    шні
    1.41
    ábado
    1.40
     of
    1.39
    確認
    1.38
    Activations Density 0.017%

    No Known Activations