© 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. 40706
    Prev
    Next
    INDEX
    Explanations

    dispose of waste

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

    references to waste disposal and getting rid of materials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on words and word-stems related to disposing or getting rid of things (e.g., dispose, disposal, disposing, rid).

    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
    </b>
    -2.78
     entram
    -1.92
    ar
    -1.76
    re
    -1.75
    _
    -1.72
    of
    -1.71
    en
    -1.66
    一股
    -1.66
    );
    -1.66
    要在
    -1.66
    POSITIVE LOGITS
     unſ
    1.86
    bebasan
    1.77
     Using
    1.75
    Yeni
    1.73
     in
    1.70
    ↵
    1.70
     advir
    1.69
     vulgaires
    1.67
    pareja
    1.57
    许多
    1.56
    Activations Density 0.019%

    No Known Activations