© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130393
    Prev
    Next
    INDEX
    Explanations

    circa or approximately values

    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
     again
    -1.83
     of
    -1.73
     contactar
    -1.71
    itzenden
    -1.70
     prüfen
    -1.70
     Mientras
    -1.66
     وقت
    -1.63
    стота
    -1.59
     \&
    -1.59
     vedea
    -1.55
    POSITIVE LOGITS
     peligroso
    1.82
    呿
    1.80
     recientes
    1.68
     кстати
    1.66
     vienas
    1.66
    UNDLE
    1.64
     the
    1.63
    hörige
    1.61
     perdiendo
    1.56
     весьма
    1.55
    Activations Density 0.007%

    No Known Activations