© 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. 22-GEMMASCOPE-RES-131K
    7. 35573
    Prev
    Next
    INDEX
    Explanations

    domain names and code

    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_22/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
    事も
    -2.59
    
    -2.45
     通过
    -2.38
     innych
    -2.36
     adjust
    -2.28
     nella
    -2.25
    谞
    -2.25
     根据
    -2.23
    ременно
    -2.19
     integrar
    -2.19
    POSITIVE LOGITS
    n
    2.59
    絅
    2.52
    zelfde
    2.48
    r
    2.44
    en
    2.41
    涠
    2.41
    呖
    2.41
    鰱
    2.34
    y
    2.31
    蹿
    2.30
    Activations Density 0.082%

    No Known Activations