© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84383
    Prev
    Next
    INDEX
    Explanations

    writing and drawing tools

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

    This neuron activates on mentions of writing or drawing tools (e.g. markers, pens, pencils).

    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
     "
    -1.61
     hundred
    -1.57
     zupełnie
    -1.48
     gamla
    -1.42
    Its
    -1.39
     muñeco
    -1.31
     sueños
    -1.30
     boneca
    -1.27
    {
    -1.27
    RE
    -1.25
    POSITIVE LOGITS
     circulación
    1.48
     Jue
    1.45
     Exams
    1.44
     jeweiligen
    1.41
     espiral
    1.40
    enyum
    1.38
    meteries
    1.34
     TRABAJO
    1.34
    ctivo
    1.33
     秋冬
    1.32
    Activations Density 0.019%

    No Known Activations