© 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. 10-GEMMASCOPE-RES-131K
    7. 15485
    Prev
    Next
    INDEX
    Explanations

    Russian, Japanese, German words

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

    The neuron fires on conjugated verb forms (inflected verbs) across multiple languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     ""
    -1.80
     heath
    -1.73
     даже
    -1.70
    ]_{\
    -1.67
     "");
    -1.66
     officinalis
    -1.66
    ’:
    -1.65
     biker
    -1.65
    s
    -1.63
     حتی
    -1.63
    POSITIVE LOGITS
    {
    2.45
     need
    2.30
     be
    1.87
     has
    1.73
    今天的
    1.70
     .
    1.70
     I
    1.69
     possibility
    1.66
     more
    1.59
     it
    1.55
    Activations Density 0.007%

    No Known Activations