© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134259
    Prev
    Next
    INDEX
    Explanations

    looking back

    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
     nele
    0.44
     jusque
    0.41
     oms
    0.39
     показателей
    0.39
     lewis
    0.38
    㑼
    0.38
     সর্বনাশ
    0.38
     diligence
    0.37
     judgements
    0.37
    炁
    0.37
    POSITIVE LOGITS
    ுள்ளது
    0.43
     назад
    0.43
     সুল
    0.42
     फ्रॉम
    0.39
    car
    0.39
     от
    0.38
    ural
    0.38
     especializado
    0.38
    origin
    0.38
     تخص
    0.38
    Activations Density 0.002%

    No Known Activations