© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10286
    Prev
    Next
    INDEX
    Explanations

    supplies

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

    The neuron activates on occurrences of the word “supplies,” especially as a section heading or list label.

    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
    ar
    -2.67
    o
    -2.63
    V
    -2.53
    or
    -2.48
    </h2>
    -2.48
    }$,
    -2.45
    歼
    -2.31
     pathetic
    -2.25
    c
    -2.23
     период
    -2.19
    POSITIVE LOGITS
    vantaged
    3.25
    葙
    2.72
    觧
    2.50
    躥
    2.45
    ATION
    2.44
    思います
    2.42
    鎹
    2.39
     esclusivamente
    2.39
     parlar
    2.33
    Clearly
    2.30
    Activations Density 0.003%

    No Known Activations