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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130986
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

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

    This neuron responds to numeric literals (digits) in source code.

    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
    ).
    -2.59
    a
    -2.31
    </h2>
    -2.08
    );
    -1.91
    N
    -1.84
    \
    -1.78
    หรือ
    -1.70
    </b>
    -1.66
    ”-
    -1.66
    U
    -1.64
    POSITIVE LOGITS
    
    1.97
    ственный
    1.95
     bús
    1.94
    夲
    1.91
    ições
    1.88
    ENCIÓN
    1.87
    뿍
    1.86
    蹋
    1.85
    </h3>
    1.84
     originalen
    1.82
    Activations Density 0.001%

    No Known Activations