© 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. 80829
    Prev
    Next
    INDEX
    Explanations

    anger management

    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
    ’
    -2.17
    …..
    -1.87
    !
    -1.82
    ....
    -1.81
    '
    -1.77
    ´
    -1.77
    !!!!!
    -1.76
     stellar
    -1.71
    .…
    -1.70
     sleek
    -1.70
    POSITIVE LOGITS
     ſol
    2.58
     vijf
    1.98
    棡
    1.88
     and
    1.87
    妧
    1.86
    ೣ
    1.85
    หรือ
    1.78
    鵙
    1.72
    樒
    1.70
     zwarte
    1.67
    Activations Density 0.025%

    No Known Activations