© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106255
    Prev
    Next
    INDEX
    Explanations

    mum names and syllables

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

    The neuron strongly activates on proper‐noun tokens beginning with the letter “M.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     PSOE
    -0.82
     Commando
    -0.81
    Pok
    -0.79
     EARL
    -0.78
     BMP
    -0.78
    Bast
    -0.76
    machten
    -0.76
    낳
    -0.76
    möglichkeiten
    -0.75
     Samar
    -0.74
    POSITIVE LOGITS
     last
    0.73
     foreign
    0.72
    baz
    0.71
    厘
    0.69
     Sicher
    0.68
     different
    0.67
    rosh
    0.67
    onski
    0.66
    スポット
    0.66
     opposite
    0.66
    Activations Density 0.035%

    No Known Activations