© 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. 32962
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
     eventually
    -1.11
     verschiedener
    -1.10
     Bezeichnung
    -1.05
     mehrerer
    -1.03
     einerseits
    -1.02
     několika
    -1.00
     見る
    -0.98
    ຣ
    -0.97
     разнообраз
    -0.96
     Posteriormente
    -0.96
    POSITIVE LOGITS
    糯米
    1.01
     EXERC
    0.92
    дна
    0.92
     togg
    0.91
     Cré
    0.91
     Elé
    0.91
    Tinh
    0.91
     Maître
    0.90
    了你
    0.89
     Ár
    0.88
    Activations Density 0.039%

    No Known Activations