© 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. 34-GEMMASCOPE-RES-131K
    7. 92420
    Prev
    Next
    INDEX
    Explanations

    pulling hair out

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

    This neuron detects idiomatic expressions of frustration involving “pulling” or “tearing” one’s hair.

    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
     acreage
    -0.71
    小林
    -0.65
    euse
    -0.63
    쿠
    -0.63
     accuse
    -0.63
    ه‌اند
    -0.61
     Nope
    -0.61
    我都
    -0.60
     toiture
    -0.60
    dası
    -0.59
    POSITIVE LOGITS
    baye
    0.72
    benzene
    0.71
    ílio
    0.69
    auri
    0.66
     loco
    0.66
    mathscr
    0.65
     agra
    0.65
     remet
    0.65
    ensk
    0.65
     Bourbon
    0.64
    Activations Density 0.145%

    No Known Activations