© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106878
    Prev
    Next
    INDEX
    Explanations

    Xanthomonas and Chantal

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific names of organisms and chemicals, particularly those starting with "Xanth".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     guerras
    -0.81
    يادة
    -0.77
    cuts
    -0.75
    stappen
    -0.75
    كتشاف
    -0.72
     terang
    -0.71
    بوع
    -0.70
    だらけ
    -0.69
     ruinas
    -0.68
    instruction
    -0.68
    POSITIVE LOGITS
    GV
    0.79
     прод
    0.77
     xan
    0.74
     ABSOL
    0.72
    proj
    0.69
    .%
    0.69
     clair
    0.69
     equestrian
    0.67
     Xan
    0.66
    itzt
    0.65
    Activations Density 0.026%

    No Known Activations