© 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. 111762
    Prev
    Next
    INDEX
    Explanations

    Wireless power, community, public

    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
     sundry
    0.48
    此
    0.40
     seasonings
    0.39
     woods
    0.39
     abiding
    0.38
     flavoring
    0.38
     perspiration
    0.38
     mags
    0.38
     letting
    0.37
     rains
    0.37
    POSITIVE LOGITS
     Ayrıca
    0.45
     आरक्षण
    0.44
    Еще
    0.43
    <unused2121>
    0.43
     группа
    0.43
    东京
    0.43
     crédit
    0.42
     пять
    0.42
    tiket
    0.42
    eará
    0.42
    Activations Density 0.001%

    No Known Activations