© 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. 75231
    Prev
    Next
    INDEX
    Explanations

    awards and prizes

    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
    Aquí
    -1.43
     velours
    -1.08
     recente
    -1.05
     nouveautés
    -1.04
     Aquí
    -1.03
     proph
    -1.03
     bershka
    -1.02
     disgra
    -1.02
     VETER
    -1.01
     aben
    -1.01
    POSITIVE LOGITS
     first
    1.55
     most
    1.50
     by
    1.36
     sehr
    1.33
     from
    1.27
     one
    1.26
     recognition
    1.23
     which
    1.22
     high
    1.19
     highly
    1.16
    Activations Density 0.032%

    No Known Activations