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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19105
    Prev
    Next
    INDEX
    Explanations

    court cases and country 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
     noin
    -1.71
    馓
    -1.70
     poils
    -1.69
     geene
    -1.68
     iconos
    -1.62
     groupes
    -1.59
     détails
    -1.59
     certains
    -1.57
     ouver
    -1.56
     feil
    -1.56
    POSITIVE LOGITS
     and
    2.48
     will
    1.89
     (
    1.72
     as
    1.61
     In
    1.59
    in
    1.59
     with
    1.56
     As
    1.56
     use
    1.52
     which
    1.50
    Activations Density 0.324%

    No Known Activations