© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    grade, stage, or aggregation

    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
    {}".
    1.61
    م
    1.60
    其
    1.44
    ার
    1.43
    ில்
    1.41
    {|\
    1.40
    ките
    1.39
    {(\
    1.35
    {}'.
    1.32
    க்
    1.31
    POSITIVE LOGITS
    nang
    1.54
    '_
    1.51
     ito
    1.43
     propos
    1.36
     adentro
    1.31
    erna
    1.29
    পূর্ন
    1.29
     elongation
    1.27
    -_
    1.26
     extremism
    1.24
    Activations Density 0.095%

    No Known Activations