© 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. 22-GEMMASCOPE-RES-131K
    7. 26560
    Prev
    Next
    INDEX
    Explanations

    specific measurements and years

    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_22/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
     longo
    -1.16
     operar
    -1.16
     escond
    -1.15
     distor
    -1.14
    FOTOS
    -1.12
    譚
    -1.11
    reiben
    -1.10
    vén
    -1.10
     it
    -1.09
     engan
    -1.09
    POSITIVE LOGITS
     of
    1.76
     moletom
    1.24
     电影
    1.21
    //};
    1.20
     couvrir
    1.14
    したが
    1.13
     ajutor
    1.12
     aproximativ
    1.11
     siguran
    1.11
     sekal
    1.09
    Activations Density 0.019%

    No Known Activations