© 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. 38630
    Prev
    Next
    INDEX
    Explanations

    too followed by adjective

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

    The neuron specifically detects occurrences of the intensifier “too” (used to mark excessive degree).

    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
    狴
    -1.87
    赑
    -1.86
    烀
    -1.85
    鈈
    -1.77
    hmmm
    -1.73
     praktisch
    -1.73
    垟
    -1.72
     nimmer
    -1.70
    
    -1.66
    extremely
    -1.66
    POSITIVE LOGITS
    </b>
    1.73
    embang
    1.69
     ....
    1.67
     manchas
    1.62
     unrelenting
    1.59
     .....
    1.56
     pushes
    1.55
     promotes
    1.55
    しちゃ
    1.53
     burgeoning
    1.51
    Activations Density 0.011%

    No Known Activations