© 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. 31-GEMMASCOPE-2-RES-65K
    7. 14662
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regions

    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_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
    ਤਾ
    0.46
     बादशाह
    0.45
    га
    0.44
    מ
    0.44
     של
    0.43
    י
    0.40
    ма
    0.40
    ט
    0.40
    בי
    0.39
    INTRODUCTION
    0.39
    POSITIVE LOGITS
     Scandinavia
    0.46
     elegant
    0.44
     Scandinavian
    0.43
     Oregon
    0.42
     Scandin
    0.42
     Pastel
    0.41
     Switzerland
    0.41
     Maine
    0.40
     Swedish
    0.40
     Nordic
    0.40
    Activations Density 0.355%

    No Known Activations