© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55102
    Prev
    Next
    INDEX
    Explanations

    suburbs and outskirts

    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_65k_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
    骞
    0.40
     ധ
    0.39
     Snell
    0.39
     স্ন
    0.39
     ion
    0.38
    творення
    0.37
     forfeited
    0.36
     onions
    0.36
     SQL
    0.35
    ⿰
    0.35
    POSITIVE LOGITS
    郊
    1.56
     suburban
    1.52
     suburbs
    1.41
     outlying
    1.34
     outskirts
    1.31
     suburb
    1.21
     countryside
    1.16
     Suburban
    1.10
     rural
    1.07
     خارج
    1.03
    Activations Density 0.067%

    No Known Activations