© 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. 84336
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    The neuron fires on capitalized identifier tokens (e.g. class names or constructor calls) 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_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
     an
    -1.92
     Adding
    -1.62
     mammoth
    -1.61
    jących
    -1.58
     one
    -1.54
     at
    -1.53
     HUGE
    -1.42
     Even
    -1.42
     Almost
    -1.40
     More
    -1.38
    POSITIVE LOGITS
     of
    1.77
     you
    1.74
     interrom
    1.67
    嫆
    1.59
    シルバー
    1.52
    ਗ਼
    1.52
     rapidement
    1.48
     BECAUSE
    1.48
     strikingly
    1.47
     ſou
    1.47
    Activations Density 0.021%

    No Known Activations