© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40050
    Prev
    Next
    INDEX
    Explanations

    XML comments for methods

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on standalone numeric literals (e.g. numbers in comments or doc-string tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    1
    -2.28
    8
    -2.00
    2
    -2.00
    6
    -1.91
    3
    -1.89
    ۹
    -1.88
    5
    -1.84
    ９
    -1.81
    長男
    -1.79
    \
    -1.73
    POSITIVE LOGITS
    ↵
    2.41
     is
    1.95
    lossians
    1.92
     to
    1.91
     there
    1.89
    acea
    1.76
     here
    1.70
     It
    1.68
        
    1.67
     If
    1.66
    Activations Density 0.002%

    No Known Activations