© 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. 3569
    Prev
    Next
    INDEX
    Explanations

    movement through

    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
    Negative Logits
    Across
    -1.45
    between
    -1.43
    Between
    -1.43
    Into
    -1.41
    across
    -1.36
    within
    -1.24
    Around
    -1.23
    Within
    -1.20
    via
    -1.17
     Between
    -1.16
    POSITIVE LOGITS
     though
    1.29
    予備
    0.81
     są
    0.79
     oude
    0.78
    though
    0.76
    freak
    0.76
     terciopelo
    0.74
    mbps
    0.73
     Hyperion
    0.72
     proporcion
    0.72
    Activations Density 0.069%

    No Known Activations