© 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. 15305
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
     Nacional
    0.80
     både
    0.80
     official
    0.77
     Classic
    0.77
    ならない
    0.73
     мероприя
    0.72
     drap
    0.72
     n
    0.72
     Zel
    0.70
     adage
    0.69
    POSITIVE LOGITS
    亮度
    1.10
    antenna
    1.09
    ally
    1.08
    स्तरीय
    1.07
    Weyl
    1.06
     الواحد
    1.03
     रास्ता
    1.02
    الب
    1.02
    niveau
    1.01
    積み
    1.01
    Activations Density 0.000%

    No Known Activations