© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99042
    Prev
    Next
    INDEX
    Explanations

    Neutron radiography

    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
     Roadster
    -0.85
     zaradi
    -0.79
    LEBR
    -0.77
    Subaru
    -0.76
    زاده
    -0.75
     DICTION
    -0.75
     shippuden
    -0.73
    궐
    -0.73
    ıyla
    -0.73
    obatan
    -0.72
    POSITIVE LOGITS
    Name
    1.37
     name
    1.31
     dtype
    1.25
     Name
    1.22
    dtype
    1.17
     Namen
    1.11
     NAME
    0.86
    ename
    0.83
                                  
    0.82
     выпу
    0.81
    Activations Density 0.010%

    No Known Activations