© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    geographical regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    kDa
    0.70
     അമ്മ
    0.65
    ロウ
    0.63
     kDa
    0.62
     pitcher
    0.61
     Downey
    0.61
     bodybuilding
    0.60
    涛
    0.60
     liquid
    0.60
    нка
    0.59
    POSITIVE LOGITS
     geographic
    3.77
     geographical
    3.73
     geography
    3.67
     Geographical
    3.56
     Geographic
    3.53
     Geography
    3.46
     geograf
    3.46
    地理
    3.42
     geospatial
    3.40
     ge
    3.31
    Activations Density 0.637%

    No Known Activations