© 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. 13711
    Prev
    Next
    INDEX
    Explanations

    code initialization

    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
    があります
    -2.42
     мужская
    -2.33
     женская
    -2.28
     面包
    -2.19
     черная
    -2.05
    缡
    -2.03
     for
    -2.02
    掼
    -2.00
    了
    -1.98
    沨
    -1.97
    POSITIVE LOGITS
    5
    3.34
    3
    3.33
    they
    3.27
    7
    2.98
    没有
    2.88
    i
    2.75
    也是
    2.70
    她
    2.70
    我
    2.59
    不是
    2.56
    Activations Density 0.002%

    No Known Activations