© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9550
    Prev
    Next
    INDEX
    Explanations

    web form elements

    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
    ’
    -2.06
    ↵
    -1.95
    </h2>
    -1.71
    s
    -1.68
     of
    -1.67
    潆
    -1.64
     we
    -1.62
     greateſt
    -1.55
     besonders
    -1.53
     примерно
    -1.53
    POSITIVE LOGITS
    ܜ
    2.11
    这一次
    2.08
    媖
    2.06
     decis
    1.99
    闥
    1.99
    ༑
    1.95
     Commissione
    1.94
    幛
    1.88
    🢐
    1.87
    鐃
    1.85
    Activations Density 0.016%

    No Known Activations