© 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. 9579
    Prev
    Next
    INDEX
    Explanations

    overexpression or Chinese small entities

    np_acts-logits-general · gemini-2.5-flash-lite

    Chinese character "小" (Xiao) and words related to size or expression in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ↵
    -3.08
    锨
    -3.02
     Their
    -2.58
     professionelle
    -2.38
     gradualmente
    -2.33
     continuamente
    -2.30
    辔
    -2.22
     alberga
    -2.22
    ݈
    -2.20
    要想
    -2.16
    POSITIVE LOGITS
    8
    3.20
    7
    3.06
    蛧
    2.94
    หรือ
    2.72
    3
    2.70
    9
    2.64
    莚
    2.53
    6
    2.52
    縢
    2.48
     workings
    2.47
    Activations Density 0.002%

    No Known Activations