© 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. 103801
    Prev
    Next
    INDEX
    Explanations

    firecrackers, METROCOM, WhiteKnuckle

    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
     zuständig
    -0.81
    noti
    -0.81
    维基
    -0.78
    ötz
    -0.77
    tà
    -0.77
     involving
    -0.76
     though
    -0.74
     contend
    -0.73
     GRADUATE
    -0.72
     niya
    -0.72
    POSITIVE LOGITS
    跹
    0.95
    这些
    0.89
     mulai
    0.89
     เรา
    0.88
     heureuse
    0.86
    OutputStream
    0.85
     kağıt
    0.83
     этих
    0.82
     pourcentage
    0.82
    information
    0.81
    Activations Density 0.067%

    No Known Activations