© 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. 10-GEMMASCOPE-RES-131K
    7. 102409
    Prev
    Next
    INDEX
    Explanations

    administrative regions

    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
    もありますが
    -1.79
     プロフィール
    -1.53
     maroc
    -1.52
     manuten
    -1.50
    لی
    -1.45
    雠
    -1.44
     vernac
    -1.42
    viève
    -1.42
    ICIENCY
    -1.41
     bolos
    -1.41
    POSITIVE LOGITS
     of
    2.39
    ↵
    1.64
     inteiro
    1.62
     fairs
    1.53
     such
    1.53
     renowned
    1.47
    しばらく
    1.47
     детской
    1.45
     takich
    1.45
     ihrer
    1.41
    Activations Density 0.064%

    No Known Activations