© 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. 74351
    Prev
    Next
    INDEX
    Explanations

    photographer

    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
    ?"
    -2.97
    .'
    -2.44
    ??????
    -2.34
    !!!!!!!!
    -2.28
    or
    -2.28
    s
    -2.19
     otros
    -2.14
    。
    -2.14
    是中国
    -2.14
    轵
    -2.13
    POSITIVE LOGITS
    .
    2.72
    蚡
    2.42
     gän
    2.39
    轫
    2.36
    葙
    2.34
     gesloten
    2.28
     bijna
    2.27
    鸸
    2.22
     belangrijke
    2.17
     vollständ
    2.13
    Activations Density 0.004%

    No Known Activations