© 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. 65202
    Prev
    Next
    INDEX
    Explanations

    social and antisocial behavior

    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
     célè
    -1.76
    鲣
    -1.74
    鹀
    -1.72
    懾
    -1.70
    楽しみです
    -1.65
    稣
    -1.64
    痦
    -1.64
    In
    -1.61
    két
    -1.59
    想到了
    -1.59
    POSITIVE LOGITS
     he
    2.09
    这
    2.05
    那些
    2.02
    这个
    1.95
    $,
    1.95
    )
    1.93
    }$,
    1.84
     aussi
    1.82
    ，
    1.80
    mathrm
    1.72
    Activations Density 0.003%

    No Known Activations