© 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. 10-GEMMASCOPE-RES-131K
    4. 9971
    Prev
    Next
    INDEX
    Explanations

    uc followed by specific tokens

    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
    㐂
    -2.72
    毉
    -2.72
    
    -2.69
    hasilkan
    -2.66
     gustado
    -2.58
    鈇
    -2.41
    ).
    -2.34
     folgender
    -2.28
     Hinsicht
    -2.27
     برای
    -2.19
    POSITIVE LOGITS
    uc
    2.86
    翃
    2.77
    "—
    2.58
    s
    2.56
    en
    2.45
    
    2.42
    但是在
    2.39
    ाउनलोड
    2.38
     ない
    2.33
    但在
    2.33
    Activations Density 0.008%

    No Known Activations