© 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. 34-GEMMASCOPE-RES-131K
    7. 93502
    Prev
    Next
    INDEX
    Explanations

    case and break statements

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

    The neuron is detecting occurrences of the keyword “break” (as used in code, especially within switch/case statements).

    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
     of
    -1.27
    Джере
    -1.06
    makeatother
    -0.99
    zember
    -0.99
     теперь
    -0.95
    関連リンク
    -0.94
    рецепт
    -0.93
    Conclusión
    -0.91
    crollView
    -0.91
    typeof
    -0.90
    POSITIVE LOGITS
     case
    1.82
     cases
    1.66
    case
    1.49
     Case
    1.39
    Case
    1.19
     caso
    1.19
    cases
    1.16
     Cases
    1.11
     default
    1.06
    や
    1.05
    Activations Density 0.001%

    No Known Activations