© 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. 58419
    Prev
    Next
    INDEX
    Explanations

    Objective-C/Swift types and classes

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

    The neuron fires on code identifiers that appear as variable or parameter names in declarations.

    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
    盉
    -1.94
     etti
    -1.93
    蚡
    -1.92
     fordi
    -1.80
     elever
    -1.74
    hopefully
    -1.73
     otel
    -1.70
     hecta
    -1.70
    ri
    -1.66
     <",
    -1.66
    POSITIVE LOGITS
     It
    2.08
     haven
    2.05
     was
    1.90
     continue
    1.84
     this
    1.80
     Still
    1.79
     
    1.74
    :
    1.72
     other
    1.72
     is
    1.71
    Activations Density 0.008%

    No Known Activations