© 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. 108730
    Prev
    Next
    INDEX
    Explanations

    code delimitation

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

    The neuron identifies code import statements (lines starting with “import”).

    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
    oldi
    -0.85
     arkiv
    -0.82
    ToEdit
    -0.81
     BaseController
    -0.79
     Ask
    -0.79
    ありがたい
    -0.77
     MatDialog
    -0.77
    dubai
    -0.77
    zése
    -0.77
    cedures
    -0.76
    POSITIVE LOGITS
     views
    0.99
    Views
    0.85
     Views
    0.85
    views
    0.84
     uitzicht
    0.81
     उन्होंने
    0.79
    veck
    0.76
    TextUtils
    0.73
    루
    0.73
    ranean
    0.72
    Activations Density 0.006%

    No Known Activations