© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112926
    Prev
    Next
    INDEX
    Explanations

    even or uneven 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
    ’
    -2.75
     возможностей
    -2.48
     serán
    -2.48
     We
    -2.23
     beträ
    -2.20
     mittlere
    -2.19
     fuß
    -2.17
    ”
    -2.17
     tendrán
    -2.16
     geringe
    -2.16
    POSITIVE LOGITS
    r
    2.69
    ſelf
    2.69
    踅
    2.61
     aé
    2.56
    warzys
    2.53
    ！！！！
    2.47
    This
    2.45
     qtd
    2.44
     guardi
    2.41
    ization
    2.36
    Activations Density 0.002%

    No Known Activations