© 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. 10-GEMMASCOPE-RES-131K
    4. 87326
    Prev
    Next
    INDEX
    Explanations

    start of quoted 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_10/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
     är
    -1.63
    ’,
    -1.53
     numerosas
    -1.52
     deutscher
    -1.45
     każdym
    -1.43
    ”,
    -1.43
     both
    -1.43
     birbir
    -1.41
     amelyek
    -1.40
     new
    -1.39
    POSITIVE LOGITS
     alcun
    1.55
     такого
    1.53
    chenen
    1.44
     caricatura
    1.42
    このように
    1.41
    5
    1.41
    The
    1.38
     Sì
    1.38
     Aktivität
    1.38
    比起
    1.37
    Activations Density 0.039%

    No Known Activations