© 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. 14188
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
     uda
    -0.97
    править
    -0.95
     کل
    -0.94
    轻易
    -0.90
     специальные
    -0.86
    ರ್
    -0.86
    🤯
    -0.82
    叼
    -0.82
     техника
    -0.81
    URCH
    -0.81
    POSITIVE LOGITS
    Two
    1.11
     rimane
    1.00
    ندية
    0.96
     two
    0.94
     aiuta
    0.91
    相変わらず
    0.90
    ığım
    0.90
     dimentic
    0.89
     sogget
    0.88
    vención
    0.86
    Activations Density 0.032%

    No Known Activations