© 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. 10-GEMMASCOPE-RES-131K
    7. 1451
    Prev
    Next
    INDEX
    Explanations

    file is part of

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

    The neuron consistently fires on the colon character that appears in code import paths (e.g. the “:” in “package:…”).

    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
    
    -1.88
    1
    -1.84
    '
    -1.74
    着头
    -1.73
     esimerkiksi
    -1.70
     gyóg
    -1.66
    泔
    -1.66
     ganzes
    -1.64
     neemt
    -1.62
    ldots
    -1.60
    POSITIVE LOGITS
     them
    1.56
    ſu
    1.55
     su
    1.55
     случи
    1.52
     values
    1.52
    曷
    1.51
     Monate
    1.50
    沨
    1.48
    Seems
    1.48
     diametro
    1.47
    Activations Density 0.007%

    No Known Activations