© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38463
    Prev
    Next
    INDEX
    Explanations

    MySQL code and transition processes

    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_22/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
     or
    -1.30
     and
    -1.18
    no
    -1.09
    ūsų
    -1.00
    y
    -0.93
    吅
    -0.92
    so
    -0.92
     like
    -0.91
     so
    -0.90
    らせ
    -0.88
    POSITIVE LOGITS
     cowok
    1.05
    ǩ
    1.04
     mauva
    1.02
     tarko
    0.99
    ОК
    0.98
    Тип
    0.98
     Wortes
    0.97
    ਫ਼
    0.97
    虽然
    0.96
    سياسي
    0.96
    Activations Density 0.038%

    No Known Activations