© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57306
    Prev
    Next
    INDEX
    Explanations

    after all

    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
    这两个
    -0.96
     fremden
    -0.95
     älteren
    -0.88
     ทั้ง
    -0.84
    &
    -0.82
     übrigen
    -0.82
     Everywhere
    -0.82
    limard
    -0.82
     üblichen
    -0.81
     zahlreiche
    -0.80
    POSITIVE LOGITS
     all
    5.84
    all
    3.52
     все
    2.63
     جميع
    1.98
    All
    1.94
     semua
    1.92
     همه
    1.91
     kaikki
    1.83
    全て
    1.80
    すべて
    1.79
    Activations Density 0.008%

    No Known Activations