© 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. 10-GEMMASCOPE-RES-131K
    7. 112178
    Prev
    Next
    INDEX
    Explanations

    hue, saturation, brightness

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

    The neuron specializes in spotting numeric values used in specifying colors (e.g. RGB/hex components, hue/saturation/brightness numbers, and named‐color codes).

    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
     <=",
    -1.20
    zeniem
    -1.18
    上的
    -1.13
    焢
    -1.10
    jder
    -1.10
    ATURES
    -1.09
     who
    -1.09
    ativeness
    -1.09
    ("")]
    -1.08
     kemeja
    -1.06
    POSITIVE LOGITS
     new
    1.27
     other
    1.25
     neuen
    1.19
    ceptre
    1.12
     newfound
    1.09
    ciąg
    1.06
     while
    1.05
    Médaille
    1.05
    طبي
    1.05
     variados
    1.05
    Activations Density 0.067%

    No Known Activations