© 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. 102037
    Prev
    Next
    INDEX
    Explanations

    annotations and programming keywords

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

    Java annotations (marked with the @ symbol).

    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
    ጢ
    -1.90
    ྥ
    -1.88
    ——–
    -1.88
    bathroom
    -1.85
    ℣
    -1.84
    甗
    -1.79
    tku
    -1.79
     to
    -1.77
    ℟
    -1.77
     znam
    -1.77
    POSITIVE LOGITS
    y
    2.95
    4
    2.78
    3
    2.50
    0
    2.36
     -
    2.30
    ,,
    2.25
    -
    2.25
    There
    2.23
    6
    2.19
     ,
    2.16
    Activations Density 0.014%

    No Known Activations