© 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. 30223
    Prev
    Next
    INDEX
    Explanations

    names and foreign words

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

    The neuron specializes in spotting personal names or user‐handle tokens in bylines or “By/Posted by” author attributions.

    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
     and
    -1.54
    cambi
    -1.06
    hax
    -0.99
    garder
    -0.98
    balon
    -0.94
     тяжело
    -0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.93
     FAVORITE
    -0.93
    türk
    -0.92
    🤪
    -0.92
    POSITIVE LOGITS
    _
    1.60
    itize
    1.40
     Erkrank
    1.33
    __
    1.30
    atized
    1.27
    ۠
    1.25
    психо
    1.22
     выбира
    1.20
     verkligen
    1.19
     största
    1.19
    Activations Density 0.032%

    No Known Activations