© 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. 86064
    Prev
    Next
    INDEX
    Explanations

    each with a

    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
     Diciembre
    -1.68
    ↵
    -1.61
     escribiendo
    -1.55
    誰
    -1.51
    Also
    -1.48
     также
    -1.48
     pinggang
    -1.48
    まず
    -1.47
    Unfortunately
    -1.47
    Currently
    -1.45
    POSITIVE LOGITS
     a
    3.06
     an
    1.59
    餍
    1.43
    茑
    1.40
    炻
    1.33
     pán
    1.32
    驁
    1.31
    诞生
    1.29
    鉿
    1.29
     funcione
    1.27
    Activations Density 0.024%

    No Known Activations