© 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. 84694
    Prev
    Next
    INDEX
    Explanations

    Core Graphics and CGAL

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

    the neuron primarily detects occurrences of the “CG” prefix (as in Core Graphics–related identifiers).

    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
    5
    -3.63
    3
    -3.33
    4
    -3.28
    6
    -3.11
    7
    -3.06
    +.
    -3.02
    0
    -3.00
    9
    -2.94
    2
    -2.91
    .
    -2.88
    POSITIVE LOGITS
     kteří
    2.84
     admiring
    2.72
     všet
    2.53
    幪
    2.50
    ebbe
    2.47
    橛
    2.45
     doskona
    2.44
     lidé
    2.44
    ir
    2.42
    Butyl
    2.41
    Activations Density 0.006%

    No Known Activations