© 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. 61463
    Prev
    Next
    INDEX
    Explanations

    oily substance

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

    The neuron activates on mentions of oily or greasy substances and related contexts (e.g., oil, grease, oily, sebum, degreasing).

    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
    ).
    -2.58
    L
    -1.95
    In
    -1.93
     ”
    -1.87
    C
    -1.73
    ?
    -1.68
    </td>
    -1.68
     It
    -1.63
    $
    -1.62
    .
    -1.61
    POSITIVE LOGITS
     oily
    1.92
    igrette
    1.85
     dijeron
    1.81
    pumpe
    1.81
    tuvo
    1.73
     sostu
    1.66
    bedienung
    1.63
    蚱
    1.59
     advir
    1.59
     murieron
    1.58
    Activations Density 0.009%

    No Known Activations