© 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. 6765
    Prev
    Next
    INDEX
    Explanations

    parts of phrases or compound words

    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
    گین
    -0.92
    labilir
    -0.86
     würd
    -0.84
    很赞
    -0.84
     такая
    -0.82
    mostly
    -0.82
    種
    -0.82
     ต้อง
    -0.81
    Mostly
    -0.81
     beware
    -0.80
    POSITIVE LOGITS
    MINUTES
    0.98
    閑
    0.94
    藁
    0.89
     quits
    0.88
     expressly
    0.86
     насеља
    0.85
    Algorithm
    0.85
     Programme
    0.85
     као
    0.84
     Budaya
    0.84
    Activations Density 0.215%

    No Known Activations