© 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. 8383
    Prev
    Next
    INDEX
    Explanations

    code package names

    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
     (
    -1.67
     and
    -1.66
     the
    -1.65
     or
    -1.46
    許多
    -1.36
    などに
    -1.36
     to
    -1.35
     our
    -1.30
     огром
    -1.29
     хорошая
    -1.21
    POSITIVE LOGITS
    趼
    1.70
     fı
    1.66
     rodo
    1.51
    亟
    1.49
     also
    1.49
     Pues
    1.47
     presa
    1.45
     alcun
    1.43
    Publié
    1.43
     then
    1.41
    Activations Density 0.358%

    No Known Activations