© 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. 83984
    Prev
    Next
    INDEX
    Explanations

    feet and inches measurement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    出一个
    -1.98
     erlä
    -1.91
     But
    -1.84
     puntas
    -1.83
    了两
    -1.76
     the
    -1.73
    一张
    -1.66
    Doesn
    -1.63
     宣传
    -1.59
     preciosas
    -1.59
    POSITIVE LOGITS
     –
    2.08
    ).
    2.05
    nellement
    1.80
     indescri
    1.77
     —
    1.77
    ↵
    1.70
    ла
    1.69
    
    1.66
    箆
    1.63
    ᯅ
    1.60
    Activations Density 0.002%

    No Known Activations