© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104572
    Prev
    Next
    INDEX
    Explanations

    types of data or code definition

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

    This neuron detects numeric literal tokens (numbers) appearing in code comments or annotations (e.g. after @var or @type).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    矬
    -1.64
    ꯠ
    -1.64
    trabajo
    -1.55
    簓
    -1.52
    Puedo
    -1.49
    yyj
    -1.49
    
    -1.49
    踯
    -1.49
    tratamiento
    -1.46
     laranja
    -1.45
    POSITIVE LOGITS
     in
    2.34
     now
    1.82
     for
    1.66
    '
    1.63
    ,
    1.62
    !
    1.52
     /
    1.48
     not
    1.47
     to
    1.46
     probably
    1.45
    Activations Density 0.001%

    No Known Activations