© 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. 65682
    Prev
    Next
    INDEX
    Explanations

    examples and samples

    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
     měla
    -0.75
    同様
    -0.75
     Reminis
    -0.74
    tened
    -0.73
    itattu
    -0.72
    受到
    -0.69
    Indy
    -0.69
     Confront
    -0.68
    hoid
    -0.67
    Gentlemen
    -0.67
    POSITIVE LOGITS
     example
    2.02
     examples
    1.91
     samples
    1.38
    examples
    1.29
    Examples
    1.23
     sample
    1.19
     péld
    1.17
    EXAMPLES
    1.14
    EXAMPLE
    1.11
    Example
    1.09
    Activations Density 0.091%

    No Known Activations