© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    sports leagues

    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
    usstsein
    -2.69
    缡
    -2.66
    艄
    -2.64
    的就
    -2.58
     the
    -2.45
    餿
    -2.45
     Increasing
    -2.39
     什么
    -2.36
    纒
    -2.30
    卨
    -2.30
    POSITIVE LOGITS
    '
    3.58
    也有
    2.55
     tne
    2.42
    גם
    2.41
    哎
    2.38
    違う
    2.36
     selben
    2.33
     burbu
    2.33
    )
    2.33
    也会
    2.31
    Activations Density 0.012%

    No Known Activations