© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130724
    Prev
    Next
    INDEX
    Explanations

    list and array enumeration

    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
     on
    -1.47
     сторона
    -1.27
     September
    -1.26
     if
    -1.16
     areas
    -1.16
     also
    -1.13
     test
    -1.12
     use
    -1.11
     in
    -1.08
    ieee
    -1.08
    POSITIVE LOGITS
     всички
    1.38
     everything
    1.30
    えっ
    1.28
     آنچه
    1.23
     いち
    1.16
    ḷ
    1.13
    हो
    1.13
    みんな
    1.11
     」
    1.10
     similaire
    1.09
    Activations Density 0.043%

    No Known Activations