© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90719
    Prev
    Next
    INDEX
    Explanations

    color gamut

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

    The neuron highlights technical color‐and‐printing terms—especially references to ink‐jet printing and color components like “color,” “gamut,” and related measurements.

    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
     he
    -1.52
     which
    -1.34
     they
    -1.27
     of
    -1.26
    ation
    -1.26
     cambia
    -1.19
    vP
    -1.16
     surrounding
    -1.16
    やった
    -1.14
    (!__
    -1.13
    POSITIVE LOGITS
    бели
    1.31
     bahagia
    1.30
    ,''
    1.30
    嶠
    1.23
    😵
    1.22
     psychosocial
    1.20
     ()=>
    1.19
    ὴν
    1.18
     biasanya
    1.18
     tarafından
    1.17
    Activations Density 0.047%

    No Known Activations