© 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. 20345
    Prev
    Next
    INDEX
    Explanations

    64-bit contexts

    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
     “(
    -2.47
    ᠌
    -2.31
    Ꮏ
    -2.31
    {~
    -2.30
    The
    -2.30
     “[
    -2.23
     jahre
    -2.20
     そば
    -2.20
     Simultaneously
    -2.19
     Another
    -2.16
    POSITIVE LOGITS
    。　　
    2.22
    是非常
    2.17
    䛗
    2.14
    鹮
    2.08
     แต่
    2.03
     洞
    2.02
    可以说是
    2.00
    笕
    1.97
    拓展
    1.95
    \
    1.93
    Activations Density 0.020%

    No Known Activations