© 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. 73279
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in expressions

    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
     only
    -1.04
    DockStyle
    -0.86
    😵
    -0.85
    九年
    -0.84
     vieta
    -0.81
    rådet
    -0.81
     ū
    -0.81
     『
    -0.81
     MessageBoxIcon
    -0.81
    Править
    -0.80
    POSITIVE LOGITS
    かっこいい
    0.88
     others
    0.87
     tipped
    0.84
    キラキラ
    0.83
    Pus
    0.82
     erhöht
    0.82
     jitter
    0.82
    きち
    0.78
     surrounded
    0.78
     prendre
    0.78
    Activations Density 0.042%

    No Known Activations