© 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. 67641
    Prev
    Next
    INDEX
    Explanations

    budget, affordable, entry-level prices

    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
     such
    -1.66
     of
    -1.56
     about
    -1.34
     from
    -1.31
     Each
    -1.30
     like
    -1.23
     through
    -1.22
     around
    -1.17
     Both
    -1.16
     different
    -1.16
    POSITIVE LOGITS
     одном
    1.37
    otriz
    1.20
    ",
    1.20
     Apakah
    1.13
     Siapa
    1.12
    দ্ধ
    1.10
    icto
    1.10
     humedad
    1.09
     [-
    1.09
     Youngstown
    1.09
    Activations Density 0.068%

    No Known Activations