© 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. 10-GEMMASCOPE-RES-131K
    4. 29155
    Prev
    Next
    INDEX
    Explanations

    any issues or differences

    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_10/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
     puni
    -1.71
     素描
    -1.69
     mauva
    -1.68
     soooo
    -1.68
     rôles
    -1.61
    produces
    -1.60
     イラストレーション
    -1.59
     手绘
    -1.58
     sooo
    -1.56
     唯美
    -1.55
    POSITIVE LOGITS
     or
    2.88
     that
    2.77
     of
    2.30
     with
    1.84
    7
    1.74
    8
    1.73
     which
    1.70
     you
    1.65
    6
    1.61
     miejsce
    1.55
    Activations Density 0.047%

    No Known Activations