© 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. 34-GEMMASCOPE-RES-131K
    7. 78469
    Prev
    Next
    INDEX
    Explanations

    code delimiters and comments

    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
    implode
    -0.96
    ❷
    -0.94
    insley
    -0.91
    Specyfikacja
    -0.90
    🦐
    -0.89
     cuaderno
    -0.88
    `${
    -0.87
    われます
    -0.86
     StatelessWidget
    -0.86
    RAEL
    -0.83
    POSITIVE LOGITS
    //
    1.09
    var
    1.00
    #
    0.98
     cubed
    0.84
    adjacency
    0.77
    Mapper
    0.77
     Necessary
    0.77
    seed
    0.75
     Mapper
    0.74
     using
    0.73
    Activations Density 0.011%

    No Known Activations