© 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. 58033
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 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
    which
    -1.70
    ↵↵
    -1.61
    when
    -1.55
    

    -1.52
    were
    -1.51
    越高
    -1.51
    very
    -1.50
    大多数
    -1.43
     квадра
    -1.43
    are
    -1.42
    POSITIVE LOGITS
    𓆉
    2.17
    婓
    1.83
     ilumina
    1.81
     técn
    1.76
    鋮
    1.74
    を設置
    1.72
    #}
    1.71
     ajustable
    1.67
     nombrado
    1.66
    ⚢
    1.63
    Activations Density 0.015%

    No Known Activations