© 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. 6990
    Prev
    Next
    INDEX
    Explanations

    is or becomes

    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
    -2.05
     from
    -1.94
     of
    -1.92
    which
    -1.66
    s
    -1.64
     which
    -1.62
    l
    -1.39
     are
    -1.38
     on
    -1.36
    to
    -1.34
    POSITIVE LOGITS
     charakterysty
    1.71
     demandé
    1.70
     portátil
    1.63
     cuarent
    1.62
     pesada
    1.61
     deudas
    1.60
     interesado
    1.58
    vlád
    1.58
    chaleco
    1.58
     több
    1.56
    Activations Density 0.112%

    No Known Activations