© 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. 50260
    Prev
    Next
    INDEX
    Explanations

    leading edge

    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
     mumbled
    -0.81
    hdr
    -0.79
     hdr
    -0.76
    CHURCH
    -0.74
    Akt
    -0.74
    gregor
    -0.73
    crop
    -0.73
    acto
    -0.72
    rú
    -0.72
    ității
    -0.72
    POSITIVE LOGITS
     leading
    2.02
    leading
    1.81
    trailing
    1.67
     trailing
    1.63
     Leading
    1.60
    Leading
    1.58
    LEADING
    1.48
    Trailing
    1.27
     веду
    1.09
     füh
    1.08
    Activations Density 0.004%

    No Known Activations