© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86754
    Prev
    Next
    INDEX
    Explanations

    Q&A coding help

    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
    ‘
    -2.13
    栳
    -1.88
     $
    -1.66
    ’
    -1.60
    慢慢
    -1.59
    ︲
    -1.59
    🢒
    -1.55
    可以
    -1.52
    ၟ
    -1.52
    ow
    -1.50
    POSITIVE LOGITS
     мужская
    1.83
     highlighting
    1.70
     Unfortunately
    1.63
     there
    1.61
     sometimes
    1.59
     Ironically
    1.59
     time
    1.58
     often
    1.57
     Although
    1.56
    Etimología
    1.55
    Activations Density 0.268%

    No Known Activations