© 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. 79173
    Prev
    Next
    INDEX
    Explanations

    lead time

    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
    клы
    -0.80
    怵
    -0.78
    ference
    -0.77
    thrift
    -0.75
    ostomy
    -0.71
    coup
    -0.71
    topped
    -0.71
    жден
    -0.71
     fonctionne
    -0.71
     kado
    -0.70
    POSITIVE LOGITS
     lead
    5.50
    Lead
    4.19
     Lead
    4.19
    lead
    4.13
     LEAD
    2.88
    LEAD
    2.86
     leads
    2.56
    リード
    2.41
     led
    2.05
     Leads
    1.98
    Activations Density 0.025%

    No Known Activations