© 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. 118538
    Prev
    Next
    INDEX
    Explanations

    older version

    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
    SOA
    -0.81
    fonte
    -0.81
    arko
    -0.79
     мировой
    -0.78
     Methuen
    -0.77
     zuen
    -0.77
    Reviewers
    -0.75
     isSet
    -0.73
    BIBLIO
    -0.73
    Mechanic
    -0.71
    POSITIVE LOGITS
     version
    2.67
     selves
    2.44
     versions
    2.42
    Version
    2.11
    version
    2.00
     Version
    1.88
     versión
    1.87
     versiones
    1.82
     Versions
    1.80
     VERSION
    1.77
    Activations Density 0.034%

    No Known Activations