© 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. 10-GEMMASCOPE-RES-131K
    7. 8358
    Prev
    Next
    INDEX
    Explanations

    CSS color values

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

    The neuron selectively fires on numeric values (digits) in CSS code—for example lengths (px, em), numeric color codes (hex digits), margins, paddings, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     inconsciente
    -1.61
    
    -1.59
    螄
    -1.59
    战胜
    -1.57
    issauga
    -1.57
     maksi
    -1.55
    糁
    -1.52
     suuri
    -1.50
     ginge
    -1.48
     zápas
    -1.48
    POSITIVE LOGITS
     of
    2.19
     or
    1.81
     from
    1.55
    0
    1.45
     at
    1.43
    8
    1.38
    9
    1.38
    7
    1.33
    5
    1.30
     L
    1.28
    Activations Density 0.008%

    No Known Activations