© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93298
    Prev
    Next
    INDEX
    Explanations

    research and publication

    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
     like
    -1.23
     сахара
    -1.20
     auriculares
    -1.16
     menciptakan
    -1.15
     ингреди
    -1.13
    Documentary
    -1.13
     pertama
    -1.11
     will
    -1.11
    pprint
    -1.09
     from
    -1.09
    POSITIVE LOGITS
     research
    2.28
    וּ
    1.61
     scientific
    1.38
     utafiti
    1.37
    ぜひ
    1.32
    ktır
    1.29
     araştır
    1.28
     Weiterbildung
    1.27
     study
    1.27
     publication
    1.27
    Activations Density 0.082%

    No Known Activations