© 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. 212290
    Prev
    Next
    INDEX
    Explanations

    geographical locations, ads, and shapes

    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
    óa
    0.43
     एक्सेल
    0.40
     Técnica
    0.40
    benz
    0.39
     பாராட்ட
    0.39
    厸
    0.37
     لگائیں
    0.37
     হন্ড
    0.37
     理
    0.37
    洴
    0.37
    POSITIVE LOGITS
     vulnerable
    0.40
     prolong
    0.37
     wok
    0.34
     enrol
    0.33
     susceptible
    0.33
    ::{
    0.33
    詹
    0.33
     taxpayer
    0.33
    حافظ
    0.33
    붉
    0.32
    Activations Density 0.003%

    No Known Activations