© 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. 120045
    Prev
    Next
    INDEX
    Explanations

    announcements and developments after "the"

    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
     may
    -2.33
     would
    -2.02
     might
    -1.97
     can
    -1.92
     could
    -1.91
     both
    -1.86
     what
    -1.83
     had
    -1.82
     if
    -1.73
     their
    -1.73
    POSITIVE LOGITS
     včetně
    1.91
    乆
    1.75
    actéristi
    1.73
    鸲
    1.71
    ਞ
    1.69
    螃
    1.69
    苼
    1.63
     ジップ
    1.62
    轳
    1.60
    ㍉
    1.57
    Activations Density 0.144%

    No Known Activations