© 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. 90691
    Prev
    Next
    INDEX
    Explanations

    Qt programming

    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
    犰
    -2.73
    馘
    -2.72
    塍
    -2.70
    檍
    -2.70
    鸲
    -2.64
    ⸂
    -2.61
    〠
    -2.58
    呖
    -2.58
    𝄆
    -2.48
    蠊
    -2.47
    POSITIVE LOGITS
    他
    3.20
    2
    2.83
    5
    2.67
    —
    2.63
     
    2.55
    8
    2.39
     Their
    2.23
    W
    2.17
    Once
    2.16
    Initially
    2.16
    Activations Density 0.000%

    No Known Activations