© 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. 10-GEMMASCOPE-RES-131K
    7. 124573
    Prev
    Next
    INDEX
    Explanations

    tutorials

    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
    驺
    -2.72
    苌
    -2.67
    pinephrine
    -2.63
     också
    -2.56
    т
    -2.50
    茕
    -2.38
    
    -2.36
    лся
    -2.31
    因为
    -2.28
    ￨
    -2.23
    POSITIVE LOGITS
    ,”
    3.44
    .
    3.20
    We
    2.95
    This
    2.95
    ’
    2.83
    The
    2.70
    While
    2.53
    Since
    2.41
     That
    2.39
    酝
    2.39
    Activations Density 0.004%

    No Known Activations