© 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. 87199
    Prev
    Next
    INDEX
    Explanations

    covered, filled, or spreading

    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
     wohin
    -1.02
     appen
    -0.99
     loro
    -0.98
     offiziell
    -0.96
    initely
    -0.95
    ”—
    -0.93
     判断
    -0.93
    orld
    -0.92
    のですか
    -0.92
     suns
    -0.92
    POSITIVE LOGITS
     the
    3.11
     every
    1.55
     our
    1.45
    település
    1.20
     everything
    1.15
    ˃
    1.10
     classrooms
    1.10
     entire
    1.07
    ̴
    1.05
     {;
    1.03
    Activations Density 0.090%

    No Known Activations