© 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. 34-GEMMASCOPE-RES-131K
    7. 80847
    Prev
    Next
    INDEX
    Explanations

    bait traps, system calls

    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
     ../../
    -0.79
     Ə
    -0.73
     Balboa
    -0.71
    cmos
    -0.70
     XVII
    -0.69
     '|
    -0.67
    owanie
    -0.66
     XXVII
    -0.65
     đựng
    -0.65
    \!
    -0.65
    POSITIVE LOGITS
    jetas
    0.76
    يكب
    0.71
     extremo
    0.69
    注入
    0.68
     policies
    0.67
    bosch
    0.67
     elementów
    0.67
     reader
    0.66
    Reader
    0.66
    Guardians
    0.66
    Activations Density 0.031%

    No Known Activations