© 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. 83843
    Prev
    Next
    INDEX
    Explanations

    be it

    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
    s
    -3.70
    man
    -3.00
    na
    -2.92
    },
    -2.89
    isième
    -2.75
     DETECTION
    -2.64
    the
    -2.61
     wasser
    -2.53
     și
    -2.50
    their
    -2.50
    POSITIVE LOGITS
     It
    3.80
     However
    3.11
     Whether
    2.92
     Unfortunately
    2.91
     únicamente
    2.75
     Personally
    2.70
    もありました
    2.59
     What
    2.55
     But
    2.48
    VIATIONS
    2.45
    Activations Density 0.020%

    No Known Activations