© 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. 22-GEMMASCOPE-RES-131K
    7. 67521
    Prev
    Next
    INDEX
    Explanations

    imports and services

    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
    ЕН
    -0.92
    PERTY
    -0.91
     教程
    -0.84
     biograf
    -0.84
    פּ
    -0.82
    נְ
    -0.82
    (^^
    -0.81
    說
    -0.81
    økt
    -0.81
    keln
    -0.81
    POSITIVE LOGITS
     messages
    0.88
     services
    0.85
     ayudó
    0.81
     permitió
    0.77
     servicio
    0.77
     zufolge
    0.75
    øs
    0.75
     years
    0.74
     campañas
    0.73
     servizi
    0.73
    Activations Density 0.050%

    No Known Activations