© 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. 25112
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns

    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
    Negative Logits
    ᵐ
    -1.02
     Geraadpleegd
    -0.93
     armé
    -0.91
     भी
    -0.90
     tiré
    -0.90
     testé
    -0.90
     الول
    -0.89
     espagnol
    -0.89
    klis
    -0.88
     Which
    -0.88
    POSITIVE LOGITS
     each
    1.08
     obtained
    1.08
     among
    1.00
    Homme
    0.99
    avatars
    0.96
    カッコ
    0.95
     Bildschirm
    0.93
     necessario
    0.92
    Atsauces
    0.91
     able
    0.90
    Activations Density 0.082%

    No Known Activations