© 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. 45623
    Prev
    Next
    INDEX
    Explanations

    "a" or "an" followed by a noun

    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
    禇
    -2.11
    ℱ
    -1.84
     fjor
    -1.84
    
    -1.84
     dziś
    -1.84
    歘
    -1.82
    俛
    -1.82
    ᳝
    -1.81
     banyo
    -1.81
     currently
    -1.81
    POSITIVE LOGITS
    ’
    1.88
    since
    1.77
    3
    1.72
    I
    1.66
    OR
    1.58
    icznie
    1.57
     luxe
    1.56
     özellikle
    1.55
    ⮑
    1.54
    </b>
    1.53
    Activations Density 0.019%

    No Known Activations