© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7884
    Prev
    Next
    INDEX
    Explanations

    food taste adjectives

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

    The neuron fires on evaluative adjectives that praise flavor, i.e. words describing something as tasty or delicious.

    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
    h
    -2.89
    t
    -2.72
    m
    -2.63
    s
    -2.56
    
    -2.47
     This
    -2.20
    𖥧
    -2.14
    泺
    -2.13
    鲵
    -2.09
     SOME
    -2.08
    POSITIVE LOGITS
    鷙
    2.73
    埽
    2.38
    熺
    2.27
    읗
    2.25
     seule
    2.20
    会儿
    2.20
     première
    2.17
    雋
    2.14
    ሖ
    2.09
    泐
    2.08
    Activations Density 0.004%

    No Known Activations