© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13415
    Prev
    Next
    INDEX
    Explanations

    desktop file paths and associations

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

    The neuron detects mentions of the “Desktop” directory in file paths.

    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
    垍
    -2.19
     has
    -2.11
     was
    -2.05
    呖
    -2.02
     mesmas
    -2.02
    惇
    -1.85
     "
    -1.84
     apoi
    -1.82
     I
    -1.81
     decisões
    -1.78
    POSITIVE LOGITS
    0
    2.44
    most
    2.41
    Some
    2.30
     После
    2.14
    Most
    2.11
    But
    2.09
    Дополнитель
    2.09
    是非常
    2.06
    時間も
    2.06
    ۔
    2.05
    Activations Density 0.003%

    No Known Activations