© 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. 41865
    Prev
    Next
    INDEX
    Explanations

    reporting speech and answers

    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
    不好意思
    -1.30
    kään
    -1.20
     to
    -1.18
     grâce
    -1.13
     montrer
    -1.12
    queles
    -1.10
    了许多
    -1.09
     zarówno
    -1.09
    minente
    -1.09
     them
    -1.08
    POSITIVE LOGITS
     there
    1.80
     ホテル
    1.18
    わけではない
    1.13
    значение
    1.13
     assists
    1.13
    otro
    1.10
    ゙
    1.09
    はある
    1.07
    tidumbre
    1.07
     場所
    1.05
    Activations Density 0.022%

    No Known Activations