© 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. 22-GEMMASCOPE-RES-131K
    7. 32946
    Prev
    Next
    INDEX
    Explanations

    dealing with or dedicated to

    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_22/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
     énon
    -1.73
     pleins
    -1.63
    toDouble
    -1.62
     clô
    -1.58
     hés
    -1.57
     renon
    -1.55
     équipé
    -1.53
     desperdic
    -1.51
     biela
    -1.49
     gants
    -1.48
    POSITIVE LOGITS
    s
    1.84
    p
    1.77
    n
    1.76
    。
    1.74
    an
    1.72
    b
    1.70
    te
    1.70
    d
    1.70
    e
    1.66
     "
    1.63
    Activations Density 0.241%

    No Known Activations