© 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. 1258
    Prev
    Next
    INDEX
    Explanations

    media franchises and names

    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
    2
    -2.91
    s
    -2.84
    1
    -2.80
    section
    -2.67
    /
    -2.41
    7
    -2.36
    尤其
    -2.30
    的
    -2.30
    3
    -2.23
    IN
    -2.19
    POSITIVE LOGITS
     jednej
    2.75
     nuestras
    2.52
    焱
    2.47
     nuestra
    2.45
     determinados
    2.34
     jednego
    2.33
    拶
    2.31
     aquellos
    2.28
     numerosos
    2.25
     jednym
    2.25
    Activations Density 0.023%

    No Known Activations