© 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. 64878
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific or technical terms, especially in biology, medicine, and computer science contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric CSS length values (e.g. “0px”) in style declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     øns
    -1.02
    其
    -0.91
     indien
    -0.90
    ográfico
    -0.90
     its
    -0.89
    bayes
    -0.88
    ятся
    -0.87
     in
    -0.87
     IB
    -0.86
     keywords
    -0.86
    POSITIVE LOGITS
     definiciones
    1.06
    ՚
    1.02
    よな
    0.99
    Aantal
    0.97
    vaila
    0.97
     動物
    0.96
     Созда
    0.94
    嗱
    0.93
     vivement
    0.92
    🧋
    0.92
    Activations Density 0.000%

    No Known Activations