© 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. 34-GEMMASCOPE-RES-131K
    4. 34804
    Prev
    Next
    INDEX
    Explanations

    Webtoon sticker download

    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_34/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
    etzten
    -0.80
    diğiniz
    -0.77
    mathbf
    -0.73
     emailed
    -0.73
    疽
    -0.73
    textStyle
    -0.73
    Eastern
    -0.72
    üchte
    -0.71
     eastern
    -0.69
    황
    -0.69
    POSITIVE LOGITS
    liff
    0.91
     Thailand
    0.90
     Sticker
    0.84
     Kano
    0.82
     thailand
    0.81
     UNT
    0.80
     obstru
    0.80
     VOD
    0.80
     Shrine
    0.80
     Muay
    0.76
    Activations Density 0.002%

    No Known Activations