© 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. 34-GEMMASCOPE-RES-131K
    7. 62668
    Prev
    Next
    INDEX
    Explanations

    cricket player Andy Bichel

    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_34/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
     Wal
    -0.98
     Don
    -0.90
    Don
    -0.86
    暱
    -0.86
     cal
    -0.83
     marzo
    -0.83
    ADDR
    -0.83
    Fun
    -0.82
     ing
    -0.81
     Bat
    -0.80
    POSITIVE LOGITS
    dür
    0.91
     ٹ
    0.90
     Wakil
    0.88
     Ff
    0.86
    Cristian
    0.85
    ських
    0.84
    Crema
    0.83
    uA
    0.82
     possam
    0.82
    שת
    0.81
    Activations Density 0.003%

    No Known Activations