© 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. 45322
    Prev
    Next
    INDEX
    Explanations

    content offset

    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
     Rainier
    -0.77
    d
    -0.75
    EMPLO
    -0.74
     kampung
    -0.73
     pressione
    -0.72
     livelli
    -0.71
     查看
    -0.71
     Pust
    -0.70
    aments
    -0.70
     premiers
    -0.70
    POSITIVE LOGITS
     offset
    1.17
    content
    1.16
     Offset
    1.16
    setContent
    1.14
     content
    1.14
     CONTENT
    0.98
     Content
    0.98
    CONTENT
    0.93
     setContent
    0.92
    offset
    0.91
    Activations Density 0.011%

    No Known Activations