© 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. 66222
    Prev
    Next
    INDEX
    Explanations

    null, none, empty, false

    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
     يول
    -0.98
     ску
    -0.88
    thodoxy
    -0.88
     Sometimes
    -0.87
     with
    -0.87
    чики
    -0.85
    сети
    -0.85
     บาง
    -0.83
     of
    -0.83
     earlier
    -0.83
    POSITIVE LOGITS
     żad
    1.03
    ไม่มี
    0.97
    chuckles
    0.96
    itamos
    0.96
     هیچ
    0.92
     gibi
    0.91
     asegura
    0.90
     nil
    0.89
    ATIVE
    0.88
     None
    0.87
    Activations Density 0.021%

    No Known Activations