© 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. 80687
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical environments ending

    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
    Từ
    -0.98
    Maharashtra
    -0.84
    بي
    -0.81
    țional
    -0.81
    thest
    -0.79
    ysł
    -0.77
    颔
    -0.77
    garmin
    -0.77
    เวลา
    -0.77
    ocardium
    -0.77
    POSITIVE LOGITS
    ちなみに
    0.89
    毕竟
    0.89
    tika
    0.88
     brooms
    0.88
    ติ
    0.87
     prunes
    0.80
     geschieht
    0.78
    ]==
    0.78
     SUL
    0.78
    kmal
    0.77
    Activations Density 0.004%

    No Known Activations