© 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. 111860
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
     
    -3.94
    );
    -3.06
    e
    -2.70
    .
    -2.50
     “
    -2.47
    -
    -2.47
      
    -2.44
    x
    -2.41
    To
    -2.34
     "
    -2.31
    POSITIVE LOGITS
    䊊
    3.31
    鵙
    3.14
    ſſel
    3.13
    鲠
    3.11
    ﮯ
    3.08
    쥘
    3.05
    Ꮀ
    2.91
    傒
    2.91
    都快
    2.88
    箧
    2.84
    Activations Density 0.009%

    No Known Activations