© 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. 34-GEMMASCOPE-RES-131K
    4. 81710
    Prev
    Next
    INDEX
    Explanations

    mouth pressure and taste

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

    the word "mouth" in various contexts.

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

    This neuron detects occurrences of the word “mouth” (including as part of compounds).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     eyesight
    -0.81
     Result
    -0.81
    良く
    -0.80
     tiefen
    -0.79
    rk
    -0.76
    ник
    -0.75
    安心して
    -0.75
     технологи
    -0.73
    Upon
    -0.71
     второго
    -0.70
    POSITIVE LOGITS
     mouth
    1.67
     Mouth
    1.55
    watering
    1.34
    Mouth
    1.32
    fuls
    1.30
    mouth
    1.27
     mouths
    1.18
    feel
    1.18
    OUTH
    1.16
    piece
    1.14
    Activations Density 0.008%

    No Known Activations