© 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. 68437
    Prev
    Next
    INDEX
    Explanations

    film releases and distribution

    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
     that
    -2.78
    łóż
    -1.42
     cómoda
    -1.41
     nemlig
    -1.34
    vestidos
    -1.34
    maquilla
    -1.32
     jaka
    -1.31
     різних
    -1.30
     regering
    -1.29
     faktisk
    -1.28
    POSITIVE LOGITS
     as
    1.25
    =("
    1.22
     by
    1.20
    ंत्र
    1.18
    受伤
    1.15
    chnen
    1.13
     like
    1.11
     её
    1.10
    包子
    1.09
    花粉
    1.09
    Activations Density 0.088%

    No Known Activations