© 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. 34-GEMMASCOPE-RES-131K
    7. 98240
    Prev
    Next
    INDEX
    Explanations

    email body content

    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_34/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
    빗
    -0.86
     aliviar
    -0.78
     slee
    -0.70
    Facet
    -0.69
    кса
    -0.69
     rosette
    -0.68
    IFEST
    -0.68
     circulación
    -0.68
     outgrowth
    -0.65
     epithet
    -0.65
    POSITIVE LOGITS
     body
    1.72
     html
    1.47
     HTML
    1.39
     bodies
    1.34
    html
    1.27
     plain
    1.14
    Html
    1.13
    HTML
    1.13
    Body
    1.07
     cuerpo
    1.07
    Activations Density 0.027%

    No Known Activations