© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78028
    Prev
    Next
    INDEX
    Explanations

    Blue followed by a specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    }:\
    -0.83
     डी
    -0.82
    brates
    -0.77
    ῥ
    -0.75
    aik
    -0.74
     uterine
    -0.74
    趔
    -0.74
    velli
    -0.73
    Ћ
    -0.73
    mane
    -0.73
    POSITIVE LOGITS
    Blue
    1.42
     Blue
    1.39
     ブルー
    1.32
     💙
    1.30
    jay
    1.28
     blue
    1.28
     蓝
    1.18
    💙
    1.16
    blue
    1.15
     BLUE
    1.15
    Activations Density 0.026%

    No Known Activations