© 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. 69323
    Prev
    Next
    INDEX
    Explanations

    20

    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
    ubakar
    -1.98
     Tentang
    -1.84
     dotato
    -1.75
     whome
    -1.73
    たまた
    -1.72
     estábamos
    -1.70
     Teléfono
    -1.70
     pensó
    -1.69
     aggiungere
    -1.68
     идут
    -1.67
    POSITIVE LOGITS
     entrar
    1.82
    </h3>
    1.81
     â
    1.75
     ï
    1.73
     строительство
    1.70
    さんは
    1.70
    未完
    1.68
     bureaucratic
    1.62
    ⽤
    1.61
    nadores
    1.59
    Activations Density 0.121%

    No Known Activations