© 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. 25241
    Prev
    Next
    INDEX
    Explanations

    food can, for You, that once

    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
    וּ
    -1.47
    LETTERS
    -1.24
     uitzicht
    -1.16
     confortable
    -1.13
    ּוֹ
    -1.12
    ־ה
    -1.12
    ждую
    -1.10
     the
    -1.09
    āja
    -1.09
     כך
    -1.08
    POSITIVE LOGITS
     cukru
    1.57
     ویتامین
    1.50
     fonti
    1.36
     ܐ
    1.30
     safe
    1.30
     حاول
    1.24
    ׇ
    1.24
    ֺ
    1.23
     vesel
    1.23
    因為
    1.22
    Activations Density 0.005%

    No Known Activations