© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79691
    Prev
    Next
    INDEX
    Explanations

    programming construct parameters

    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
     />";
    -0.88
    colm
    -0.84
     alkot
    -0.83
    don
    -0.82
     ส่ง
    -0.82
    Don
    -0.81
     SafeMath
    -0.81
    s
    -0.81
     prowadzi
    -0.81
     sprawia
    -0.81
    POSITIVE LOGITS
    Trama
    1.11
     veya
    1.03
     or
    1.03
    Selamat
    0.94
    Ingredi
    0.93
    Mitä
    0.93
    Minha
    0.92
    厌
    0.92
    Solu
    0.90
    жаться
    0.89
    Activations Density 0.005%

    No Known Activations