© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5733
    Prev
    Next
    INDEX
    Explanations

    blue, bluish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    Broadway
    0.45
    Organic
    0.45
    Bris
    0.43
    ageddon
    0.43
    endous
    0.43
    ⧐
    0.43
    Accounting
    0.41
    Decedent
    0.41
    Diverse
    0.41
    เปลี่ยน
    0.40
    POSITIVE LOGITS
     blue
    1.42
     Blue
    1.28
    blue
    1.21
     bluish
    1.20
    Blue
    1.19
    蓝色
    1.13
    藍
    1.13
     블루
    1.13
     azul
    1.12
     BLUE
    1.12
    Activations Density 0.122%

    No Known Activations