© 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. 104932
    Prev
    Next
    INDEX
    Explanations

    curly braces

    np_acts-logits-general · gemini-2.5-flash-lite

    curly braces and similar bracketing symbols in code or technical text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     ligeramente
    -2.11
     profundamente
    -1.99
    謇
    -1.95
    啣
    -1.95
    囂
    -1.94
     densidad
    -1.92
     别
    -1.90
    </sub>
    -1.89
     estrictamente
    -1.88
    Sonntag
    -1.80
    POSITIVE LOGITS
     \
    2.81
    ’
    2.41
     ‘
    2.33
     \&
    2.30
    '
    1.99
     comunica
    1.95
    「
    1.94
    “
    1.93
     a
    1.92
    >
    1.92
    Activations Density 0.156%

    No Known Activations