© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67532
    Prev
    Next
    INDEX
    Explanations

    code keywords and separators

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

    The neuron fires on discussion of duplicate or repeated items—e.g. words like “repeat,” “elements,” “previous,” “value,” and “example” when describing repeated elements 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_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
     المنتج
    -0.91
     condescending
    -0.88
    स्व
    -0.87
     disasters
    -0.87
     durante
    -0.86
    Acer
    -0.85
     increíbles
    -0.85
    halten
    -0.84
     Reis
    -0.84
     abrazo
    -0.82
    POSITIVE LOGITS
     after
    1.27
     those
    1.16
     three
    1.10
     because
    1.09
     Because
    1.00
     moved
    1.00
     changed
    0.98
     despite
    0.98
     While
    0.98
     showed
    0.98
    Activations Density 0.001%

    No Known Activations