© 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. 6912
    Prev
    Next
    INDEX
    Explanations

    compound words ending in head

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    e
    -2.53
    er
    -2.33
    縯
    -2.25
    でしたが
    -2.11
    
    -2.08
     stumbling
    -2.06
     étab
    -2.05
     şir
    -2.03
     December
    -1.98
    あまり
    -1.92
    POSITIVE LOGITS
    狴
    3.11
    '
    3.02
    赑
    2.97
    雠
    2.92
    祧
    2.77
    那我
    2.73
    actéristi
    2.67
    詎
    2.67
    head
    2.59
    튿
    2.59
    Activations Density 0.007%

    No Known Activations