© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2229
    Prev
    Next
    INDEX
    Explanations

    explaining meaning or definition

    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
    Not in Any Lists

    No Comments

    Negative Logits
    st
    3.06
    ي
    2.89
    das
    2.87
    意见
    2.84
    dw
    2.80
    rences
    2.76
     semangat
    2.67
    鏄
    2.64
    rmse
    2.63
    de
    2.62
    POSITIVE LOGITS
    ل
    4.88
    ﾟ
    2.89
    匚
    2.87
    ਰ
    2.74
     grudge
    2.73
    ور
    2.65
     byť
    2.63
    ỗi
    2.63
    ל
    2.59
    لنا
    2.56
    Activations Density 0.360%

    No Known Activations