© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5298
    Prev
    Next
    INDEX
    Explanations

    color blue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     रथ
    0.82
     Waugh
    0.79
     Feria
    0.75
     Schwarzenegger
    0.75
    冼
    0.75
    ότητας
    0.74
    EXIT
    0.73
    worms
    0.70
    isserie
    0.70
    춘
    0.69
    POSITIVE LOGITS
     blue
    2.44
     Blue
    2.44
    Blue
    2.33
     BLUE
    2.19
    blue
    2.18
    BLUE
    1.92
    蓝
    1.90
     ブルー
    1.88
     blu
    1.81
    ブルー
    1.79
    Activations Density 0.125%

    No Known Activations