© 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. 10202
    Prev
    Next
    INDEX
    Explanations

    anime and animated series

    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
     there
    -1.52
     Makes
    -1.21
     with
    -1.11
    óval
    -1.06
     you
    -1.03
    亙
    -1.01
     olmak
    -1.01
     think
    -1.00
    ),
    -1.00
     at
    -1.00
    POSITIVE LOGITS
    鮠
    1.22
    ابراین
    1.21
     why
    1.21
    瘊
    1.19
    animation
    1.19
     刺繍
    1.17
    导演
    1.16
    omorph
    1.16
    毟
    1.14
     Gogh
    1.13
    Activations Density 0.056%

    No Known Activations