© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122282
    Prev
    Next
    INDEX
    Explanations

    Massachusetts and Boston

    np_acts-logits-general · gemini-2.5-flash-lite

    boston, massachusetts, hospital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ecu
    0.50
    疟
    0.49
     छत्तीसगढ़
    0.47
     হিন্দি
    0.46
     छत्तीस
    0.46
     Emirati
    0.45
     Ecuadorian
    0.43
    utani
    0.43
     الإمارات
    0.43
    凭
    0.42
    POSITIVE LOGITS
     Massachusetts
    1.53
    Boston
    1.51
    Massachusetts
    1.51
     Boston
    1.48
     boston
    1.27
    boston
    1.26
    BOSTON
    1.25
     Celtics
    0.96
    Harvard
    0.94
     Harvard
    0.93
    Activations Density 0.199%

    No Known Activations