© 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. 102313
    Prev
    Next
    INDEX
    Explanations

    hug and cuddle

    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
    งิน
    -2.88
    鸲
    -2.58
     It
    -2.52
    特有
    -2.50
     recognises
    -2.48
     you
    -2.47
     emphasised
    -2.42
    诹
    -2.28
    ครื่อง
    -2.25
    に於
    -2.23
    POSITIVE LOGITS
    薆
    2.75
     étab
    2.69
    久し
    2.56
    $
    2.53
    *
    2.44
    蟊
    2.36
     perseverance
    2.23
    ations
    2.20
     ……
    2.19
    ㉕
    2.19
    Activations Density 0.002%

    No Known Activations