© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11451
    Prev
    Next
    INDEX
    Explanations

    career, sports, arts, philosophy

    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_22/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
     [];
    -1.13
     and
    -0.98
    </h2>
    -0.97
    ']
    
    -0.96
     enticing
    -0.94
     प्रत्येक
    -0.94
    <!--
    
    -0.93
     大人
    -0.93
     on
    -0.90
     eight
    -0.90
    POSITIVE LOGITS
     kanskje
    1.25
     utford
    1.20
     opravdu
    1.20
     egentlig
    1.16
     spørs
    1.15
    がこの
    1.14
    primarily
    1.12
     åp
    1.12
     skjø
    1.10
     smtplib
    1.09
    Activations Density 0.159%

    No Known Activations