© 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. 17-GEMMASCOPE-2-RES-16K
    7. 12952
    Prev
    Next
    INDEX
    Explanations

    event dispatch and handling

    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_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
    ب
    2.83
    ﺗ
    2.81
    ير
    2.61
    +}^{
    2.61
     adduced
    2.51
    𝘧
    2.48
    alas
    2.43
    𝘨
    2.43
    殑
    2.39
    venta
    2.38
    POSITIVE LOGITS
    yrs
    3.12
    ాన్ని
    2.72
    به
    2.58
     tiempo
    2.53
     okolo
    2.53
    ం
    2.49
    з
    2.43
    basecode
    2.40
     Considerable
    2.37
    eau
    2.36
    Activations Density 0.236%

    No Known Activations