© 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. 92461
    Prev
    Next
    INDEX
    Explanations

    idols and subunits

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

    The neuron fires on mentions of the Japanese idol‐metal band “Babymetal” (and their song/album titles like “Gimme Chocolate!!”).

    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
    իմ
    -0.75
     amig
    -0.71
     ocup
    -0.71
    Εκ
    -0.71
    nother
    -0.69
    æn
    -0.69
     intelectual
    -0.66
    Obituary
    -0.66
    {}\
    -0.66
    arnia
    -0.66
    POSITIVE LOGITS
     subunit
    1.03
     Aq
    0.98
     épisodes
    0.92
     subunits
    0.86
     Uran
    0.85
     Scouting
    0.85
     idols
    0.83
    ftone
    0.82
     scouting
    0.82
    偶像
    0.80
    Activations Density 0.006%

    No Known Activations