© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80989
    Prev
    Next
    INDEX
    Explanations

    trace and track paths

    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
    ítu
    -0.77
    KeyCode
    -0.76
     vál
    -0.75
     on
    -0.71
     vys
    -0.70
     бен
    -0.69
    の見
    -0.69
     Wieder
    -0.68
    Interpretation
    -0.68
    ък
    -0.66
    POSITIVE LOGITS
     traced
    4.75
     tracing
    4.69
     trace
    4.69
    trace
    3.98
     Tracing
    3.97
    Tracing
    3.91
     Trace
    3.72
    tracing
    3.70
    Trace
    3.66
     traceable
    3.56
    Activations Density 0.114%

    No Known Activations