© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57050
    Prev
    Next
    INDEX
    Explanations

    code declarations and method calls

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

    The neuron is a detector for numeric literals (plain numbers) appearing in 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_34/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
     focused
    -0.84
    ev
    -0.83
     gives
    -0.77
    </strong>
    -0.76
    興趣
    -0.76
    пів
    -0.75
    护理
    -0.72
     Going
    -0.72
     brings
    -0.72
    rana
    -0.71
    POSITIVE LOGITS
     遮
    0.92
    Eigenschaften
    0.87
     ampliación
    0.86
    Anche
    0.84
     něj
    0.84
     IAA
    0.84
     увеличить
    0.84
     anty
    0.84
    Daha
    0.83
    upaten
    0.82
    Activations Density 0.003%

    No Known Activations