© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35781
    Prev
    Next
    INDEX
    Explanations

    programming and math symbols

    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
    arques
    -1.11
    jší
    -0.92
    ální
    -0.91
    entamiento
    -0.87
    蛟
    -0.86
    LayoutConstraint
    -0.86
    の人に
    -0.85
    沁
    -0.83
    rasing
    -0.83
     mulheres
    -0.83
    POSITIVE LOGITS
    够
    0.86
    夠
    0.85
    もあって
    0.81
    是个
    0.79
    澆
    0.79
     other
    0.77
     battaglia
    0.76
    なども
    0.75
     erected
    0.75
    もありました
    0.75
    Activations Density 0.025%

    No Known Activations