© 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. 43802
    Prev
    Next
    INDEX
    Explanations

    scent

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

    words related to scents, fragrances, and aromas, particularly when describing their presence or characteristics.

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

    The main thing this neuron does is detect words referring to scent or fragrance.

    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
    s
    -3.14
     như
    -2.63
    ペーン
    -2.52
    ”
    -2.42
    ností
    -2.41
    os
    -2.36
     oleh
    -2.33
    我們
    -2.31
     seperti
    -2.30
    ৄ
    -2.16
    POSITIVE LOGITS
    ’
    3.22
     donnent
    2.13
    佮
    2.08
    "
    2.05
    竞争
    2.05
    ⵌ
    2.03
     การ
    2.00
     legt
    1.98
    泂
    1.97
     offene
    1.96
    Activations Density 0.002%

    No Known Activations