© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3005
    Prev
    Next
    INDEX
    Explanations

    street names and avenues

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     অ্যান
    0.26
    鲵
    0.24
     CharPtr
    0.24
     Hỏi
    0.24
    药物
    0.24
     βοη
    0.24
     एंटीऑ
    0.24
    字符串
    0.23
    ல்களில்
    0.23
    轺
    0.23
    POSITIVE LOGITS
     metro
    0.38
     suburbs
    0.34
     neighbourhoods
    0.34
     subway
    0.34
     boulevard
    0.33
     मेट्रो
    0.33
     Metro
    0.32
    Metro
    0.32
     metropolitan
    0.31
     Metropolitan
    0.29
    Activations Density 0.053%

    No Known Activations