© 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. 10-GEMMASCOPE-RES-131K
    7. 19407
    Prev
    Next
    INDEX
    Explanations

    Wellesley College, IANS, entrants, PLoS ONE

    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
     After
    -3.16
     Following
    -3.13
     Because
    -2.92
     Most
    -2.72
    It
    -2.67
     Various
    -2.67
    ization
    -2.63
    There
    -2.61
    ра
    -2.59
     Other
    -2.53
    POSITIVE LOGITS
    轳
    3.39
    埽
    3.23
    䜣
    3.05
    俛
    3.00
    ing
    2.89
    胳
    2.88
    ﱠ
    2.86
    缑
    2.78
    謦
    2.70
    螂
    2.67
    Activations Density 0.023%

    No Known Activations