© 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. 34-GEMMASCOPE-RES-131K
    7. 91013
    Prev
    Next
    INDEX
    Explanations

    materials and supplies

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

    This neuron fires on document structural headings—titles, step labels, and section/subsection names (e.g. “You Will Need:”, “Step 1:”, “Tools”, “How We Did It”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Например
    -0.89
     kampen
    -0.89
    čkou
    -0.86
    ૬
    -0.83
     取り付け
    -0.83
     göm
    -0.82
    Примеры
    -0.80
    𝒒
    -0.80
     κάπο
    -0.79
    Història
    -0.79
    POSITIVE LOGITS
     materials
    2.53
     supplies
    2.38
    Materials
    2.22
     Materials
    2.13
    MATERIALS
    2.09
     ingredients
    2.02
     equipment
    1.93
     Supplies
    1.86
    materials
    1.85
     MATERIALS
    1.82
    Activations Density 0.058%

    No Known Activations