© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    Boston and Harvard locations

    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
    岐阜
    1.10
     Jharkhand
    1.02
    郧
    0.97
     Ranchi
    0.95
     रांची
    0.94
     Niger
    0.92
     Astana
    0.90
     Казахстан
    0.89
    鄂
    0.85
     झारखंड
    0.85
    POSITIVE LOGITS
     Boston
    3.26
     Massachusetts
    3.23
    Massachusetts
    3.23
    Boston
    3.15
     boston
    2.82
    boston
    2.64
    BOSTON
    2.56
     Harvard
    2.32
     Celtics
    2.23
    Harvard
    2.19
    Activations Density 0.117%

    No Known Activations