© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13800
    Prev
    Next
    INDEX
    Explanations

    structured comparative data

    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_22_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
    trad
    0.59
    \
    0.59
     trad
    0.59
     Trad
    0.59
     SIC
    0.58
    (*
    0.58
    Trad
    0.58
     out
    0.57
     (
    0.57
    ConnectionString
    0.57
    POSITIVE LOGITS
    <unused35>
    0.81
     kannst
    0.74
    <unused21>
    0.72
     কুক
    0.72
    ENDMENT
    0.71
    <unused49>
    0.70
    ineros
    0.70
    ларды
    0.70
    elected
    0.69
    堭
    0.69
    Activations Density 0.014%

    No Known Activations