© 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. 58344
    Prev
    Next
    INDEX
    Explanations

    best wishes and regards

    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
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -2.20
    4
    -1.91
    8
    -1.84
    9
    -1.83
    6
    -1.74
    ౮
    -1.74
     exceptionally
    -1.71
     ciudadana
    -1.64
    赜
    -1.63
    你也
    -1.63
    POSITIVE LOGITS
     and
    1.86
     during
    1.50
    始まり
    1.49
     because
    1.45
     nicknamed
    1.44
    ministrazione
    1.39
    毘
    1.38
     to
    1.38
    ՞
    1.38
     sizable
    1.27
    Activations Density 0.010%

    No Known Activations