© 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. 83110
    Prev
    Next
    INDEX
    Explanations

    Mount or Mt followed by place names

    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
    ாய
    -0.90
     himmel
    -0.79
     olvidar
    -0.79
     Ін
    -0.78
     отличие
    -0.78
    Dap
    -0.77
    诣
    -0.76
    稈
    -0.73
    ğını
    -0.73
     arată
    -0.72
    POSITIVE LOGITS
    Mount
    0.92
    Mt
    0.81
     Mount
    0.81
    桑
    0.77
     Mt
    0.77
    Галерея
    0.77
     Folgen
    0.75
     стан
    0.75
     fastened
    0.75
    iros
    0.72
    Activations Density 0.012%

    No Known Activations