© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9515
    Prev
    Next
    INDEX
    Explanations

    colors, specific shades, descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nivel
    0.79
     photons
    0.79
     exager
    0.78
    效果
    0.77
     SUBSTITUTE
    0.76
     provoqu
    0.76
    閾
    0.76
     Photoshop
    0.76
     foreground
    0.75
    阈
    0.75
    POSITIVE LOGITS
     Colors
    1.23
     colors
    1.21
    Colors
    1.21
    colors
    1.21
     colours
    1.15
     warna
    1.15
     COLORS
    1.07
    สี
    1.05
     kleuren
    1.03
     Colours
    1.03
    Activations Density 0.204%

    No Known Activations