© 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. 40263
    Prev
    Next
    INDEX
    Explanations

    CSIRO, helpers, HCC, classnames

    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
    。
    -2.69
    \
    -2.34
    ми
    -2.27
    ）
    -2.20
    喈
    -2.19
     защиту
    -2.11
     of
    -2.08
    ).
    -2.06
    )$
    -2.02
    
    -1.98
    POSITIVE LOGITS
    d
    2.50
     What
    2.23
     думать
    1.98
    躊
    1.92
     Much
    1.92
    けれ
    1.91
     It
    1.88
     Many
    1.88
    这件事情
    1.84
     Roughly
    1.83
    Activations Density 0.020%

    No Known Activations