© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129532
    Prev
    Next
    INDEX
    Explanations

    hydrothermal, names, technical terms

    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
    ка
    -3.33
    re
    -2.64
    al
    -2.63
    ar
    -2.63
    other
    -2.45
    ul
    -2.36
    '
    -2.34
    喑
    -2.34
     другие
    -2.34
    所得
    -2.33
    POSITIVE LOGITS
    栳
    2.77
    𞤤
    2.66
     exiled
    2.64
     erfordert
    2.47
    无比
    2.45
    却不
    2.31
    𝐒
    2.31
    教えて
    2.30
    ﺢ
    2.28
     resurrected
    2.22
    Activations Density 0.063%

    No Known Activations