© 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. 42242
    Prev
    Next
    INDEX
    Explanations

    questions and statements of uncertainty

    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
    b
    -1.70
    p
    -1.65
    c
    -1.62
    o
    -1.55
    or
    -1.47
    ana
    -1.46
    1
    -1.46
    ings
    -1.46
    w
    -1.46
    ca
    -1.45
    POSITIVE LOGITS
    asics
    1.44
     古风
    1.36
    liun
    1.33
    nesto
    1.33
    👋
    1.30
     撮っ
    1.30
    🖤
    1.29
    ❕
    1.28
     Reforma
    1.27
    mā
    1.27
    Activations Density 0.046%

    No Known Activations