© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1204
    Prev
    Next
    INDEX
    Explanations

    hex color codes

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

    This neuron detects mentions of color channel formats and functions (e.g. ARGB, RGBA, color conversion/extraction).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    XMLSchema
    -0.73
    ilk
    -0.72
     塩
    -0.71
    getType
    -0.69
    ministrazione
    -0.69
     штука
    -0.69
    вши
    -0.69
    )：
    -0.68
     😘
    -0.68
     fromage
    -0.68
    POSITIVE LOGITS
     Masks
    0.85
    Statut
    0.82
     idee
    0.79
     masks
    0.78
    órm
    0.75
    δικ
    0.74
    Tekst
    0.73
    Infla
    0.73
     insur
    0.71
    Milit
    0.71
    Activations Density 0.012%

    No Known Activations