© 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. 106273
    Prev
    Next
    INDEX
    Explanations

    marred or month

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

    This neuron activates on tokens that contain the character “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
    だが
    -0.77
     berkomunikasi
    -0.76
    ckeditor
    -0.76
     mempelajari
    -0.75
     melindungi
    -0.75
    芸術
    -0.75
    但却
    -0.73
    된
    -0.71
     Exeter
    -0.70
    サキ
    -0.69
    POSITIVE LOGITS
    methods
    1.07
     María
    1.02
     monitored
    1.02
     METHODOLOGY
    1.00
     militaires
    0.99
     Maintain
    0.98
     MARKETS
    0.98
    thod
    0.97
    Mostrar
    0.97
    members
    0.96
    Activations Density 0.134%

    No Known Activations