© 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. 22722
    Prev
    Next
    INDEX
    Explanations

    with the noun phrase

    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
    ’
    -2.67
    𓆜
    -2.30
    *);
    -2.14
    =’
    -2.03
     חיצוני
    -2.02
    "";
    -1.99
     willingly
    -1.95
     became
    -1.93
    
    -1.90
    ).)
    -1.88
    POSITIVE LOGITS
     regard
    3.91
    a
    3.25
    ing
    3.19
     regards
    3.19
    the
    2.66
     Hence
    2.52
     وإ
    2.50
    stood
    2.47
     Therefore
    2.41
    standing
    2.38
    Activations Density 0.076%

    No Known Activations