© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99047
    Prev
    Next
    INDEX
    Explanations

    case...break

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

    This neuron detects the presence of switch‐case (and related select) control‐flow constructs 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
     hina
    -0.85
     coreana
    -0.85
    くない
    -0.84
    jących
    -0.81
    𝗈
    -0.79
    Handbook
    -0.78
     inovasi
    -0.77
    Ciclo
    -0.75
     bogor
    -0.75
    Keynote
    -0.75
    POSITIVE LOGITS
     case
    1.40
    case
    1.03
     cases
    1.02
     mad
    0.96
    剿
    0.90
     HI
    0.89
     cin
    0.88
     Media
    0.86
     break
    0.86
     tube
    0.86
    Activations Density 0.002%

    No Known Activations