© 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. 61255
    Prev
    Next
    INDEX
    Explanations

    software documentation and dependencies

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

    The neuron detects occurrences of software library or module names (often alongside their version numbers).

    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
    (
    -1.78
     the
    -1.76
    s
    -1.41
     we
    -1.34
     &
    -1.30
     has
    -1.29
     each
    -1.29
    e
    -1.29
    y
    -1.23
    a
    -1.20
    POSITIVE LOGITS
     mennesker
    1.51
     französische
    1.34
     récente
    1.34
    pagnole
    1.33
    lloworld
    1.30
    VERTISING
    1.30
     cualquier
    1.30
     그것
    1.28
     perv
    1.27
    CHOOL
    1.26
    Activations Density 0.105%

    No Known Activations