© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2684
    Prev
    Next
    INDEX
    Explanations

    main followed by category or subject

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dashed
    1.99
    dashed
    1.66
    𝐔
    1.57
    ciano
    1.50
     Klicken
    1.50
    Huge
    1.49
     Lage
    1.49
    𝐁
    1.49
    وني
    1.48
    𝐌
    1.47
    POSITIVE LOGITS
    𝗳
    1.61
    ের
    1.60
    ع
    1.59
     beteil
    1.51
    larını
    1.51
    اتها
    1.49
    ята
    1.49
    ер
    1.45
    ات
    1.44
     coveredmethods
    1.42
    Activations Density 0.196%

    No Known Activations