© 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. 42129
    Prev
    Next
    INDEX
    Explanations

    years of duration

    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
    諄
    -1.71
    韪
    -1.69
    ↵↵
    -1.66
    arım
    -1.66
    毖
    -1.65
    皚
    -1.63
    หรือ
    -1.58
    tentu
    -1.55
    戇
    -1.52
    isière
    -1.51
    POSITIVE LOGITS
     of
    2.72
    f
    2.03
    </h3>
    1.99
     attore
    1.79
    in
    1.76
    戋
    1.63
    s
    1.63
    h
    1.59
    di
    1.55
    C
    1.55
    Activations Density 0.033%

    No Known Activations