© 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. 22-GEMMASCOPE-RES-131K
    7. 16173
    Prev
    Next
    INDEX
    Explanations

    special characters and programming keywords

    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
    獰
    -1.02
     krótk
    -0.99
     коротки
    -0.96
     beserta
    -0.95
    čnej
    -0.94
     entière
    -0.94
    ográ
    -0.92
    そして
    -0.91
     its
    -0.90
     two
    -0.88
    POSITIVE LOGITS
     inapropiados
    1.00
     действует
    0.99
     деревьев
    0.94
    鯔
    0.94
    竟然是
    0.94
     圈
    0.92
     السلطة
    0.91
     sofrer
    0.90
    ِّ
    0.89
    ִּ
    0.89
    Activations Density 0.072%

    No Known Activations