© 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. 10-GEMMASCOPE-RES-131K
    4. 102187
    Prev
    Next
    INDEX
    Explanations

    freaking out

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

    The neuron activates strongly on informal “freak out” expressions (e.g. “freaking out,” “freaked out”).

    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
    䉴
    -1.82
    勍
    -1.76
     Anſ
    -1.74
    엥
    -1.73
    asthan
    -1.68
     erlä
    -1.67
     начали
    -1.67
    Preparación
    -1.66
    憮
    -1.65
     sebelum
    -1.62
    POSITIVE LOGITS
    .
    2.27
    M
    1.95
    T
    1.88
    {
    1.88
    \
    1.86
    H
    1.85
    },
    1.83
    culoskeletal
    1.70
    ↵↵↵
    1.68
    しら
    1.64
    Activations Density 0.006%

    No Known Activations