© 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. 86145
    Prev
    Next
    INDEX
    Explanations

    lat followed by key endings

    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
    CurtirCurtir
    -2.81
    傩
    -2.75
     soñ
    -2.63
    ztes
    -2.56
    嫘
    -2.50
    龊
    -2.48
    怍
    -2.48
     笔画
    -2.48
    綃
    -2.48
     Bedür
    -2.45
    POSITIVE LOGITS
    \
    3.72
    3
    3.27
    6
    2.89
    '
    2.88
    s
    2.86
    4
    2.80
     '
    2.78
     begge
    2.58
    b
    2.52
    一些
    2.48
    Activations Density 0.012%

    No Known Activations