© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93065
    Prev
    Next
    INDEX
    Explanations

    function parameter documentation

    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
    emplares
    -1.13
    ﮦ
    -1.09
    Ваш
    -1.07
    に見える
    -1.05
    Bringing
    -1.05
     همچنین
    -1.05
    ㄀
    -1.03
    Хотя
    -1.02
    brought
    -1.02
    accessoires
    -1.02
    POSITIVE LOGITS
    ?
    1.20
    飲食
    0.94
    []
    
    0.88
    結果
    0.87
    .
    0.85
     ۱۳۸
    0.85
     cæ
    0.85
     noft
    0.84
    岁的
    0.84
     fuch
    0.83
    Activations Density 0.001%

    No Known Activations