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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103123
    Prev
    Next
    INDEX
    Explanations

    foster collaboration and community

    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_10/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
    戽
    -2.67
    缑
    -2.61
     patrie
    -2.58
     agricole
    -2.53
     bricola
    -2.50
    猡
    -2.50
    蚰
    -2.41
    醅
    -2.38
    垸
    -2.38
     avocat
    -2.36
    POSITIVE LOGITS
    >
    2.72
     Then
    2.59
    m
    2.45
    是由
    2.45
    м
    2.41
    k
    2.36
    This
    2.31
    o
    2.27
     «
    2.25
     —
    2.16
    Activations Density 0.003%

    No Known Activations