© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14017
    Prev
    Next
    INDEX
    Explanations

    API calls and data sources

    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
     після
    -1.63
     ketika
    -1.62
     после
    -1.57
     setelah
    -1.45
     sebagai
    -1.40
     cuando
    -1.39
     ancak
    -1.34
     цього
    -1.32
     seperti
    -1.30
     jika
    -1.29
    POSITIVE LOGITS
     Ahnung
    1.53
    .
    1.20
    んですよね
    1.20
    さまざま
    1.17
     a
    1.15
    様々
    1.13
    неры
    1.13
     website
    1.12
     about
    1.09
     websites
    1.09
    Activations Density 0.062%

    No Known Activations