© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    tools

    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
    s
    -2.09
    ’
    -2.03
    i
    -1.97
     childish
    -1.70
     superficial
    -1.69
    e
    -1.67
    ea
    -1.63
    et
    -1.62
     andre
    -1.59
     丽
    -1.56
    POSITIVE LOGITS
    There
    2.02
     recently
    1.98
    These
    1.95
     erweit
    1.86
    They
    1.83
     schli
    1.83
     vermag
    1.81
    通常
    1.76
     rédig
    1.76
    Furthermore
    1.75
    Activations Density 0.021%

    No Known Activations