© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2114
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    賈
    0.26
    血管
    0.25
    峒
    0.24
     algodón
    0.23
     綿
    0.22
     communautés
    0.22
    ᠴ
    0.22
     、,
    0.22
    ⁽
    0.22
     diarrhoea
    0.22
    POSITIVE LOGITS
    if
    0.60
     if
    0.36
    continue
    0.32
    emit
    0.29
    setTimeout
    0.29
    this
    0.28
    while
    0.28
    fprintf
    0.28
    temp
    0.27
    switch
    0.27
    Activations Density 0.130%

    No Known Activations