© 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. 71521
    Prev
    Next
    INDEX
    Explanations

    legal documents and software licenses

    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
    p
    -1.64
    l
    -1.54
    f
    -1.52
    d
    -1.45
    M
    -1.41
    k
    -1.34
    el
    -1.34
     gets
    -1.34
     substantially
    -1.31
     As
    -1.30
    POSITIVE LOGITS
    ㆆ
    1.60
    depuis
    1.60
     leſs
    1.51
    jusqu
    1.51
    숑
    1.48
     Besoin
    1.48
     Réponses
    1.47
     Désolé
    1.46
     siè
    1.43
     interrom
    1.42
    Activations Density 0.274%

    No Known Activations