© 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. 177
    Prev
    Next
    INDEX
    Explanations

    largest geographical entities

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

    most common or best method

    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
    彳
    0.42
    都很
    0.41
    的很
    0.41
    ەیە
    0.41
    ('/\
    0.38
    新たな
    0.38
     Instances
    0.38
     nêu
    0.38
    様子
    0.38
    fdata
    0.37
    POSITIVE LOGITS
    之一
    0.71
    🥇
    0.62
     EVER
    0.61
     imaginable
    0.59
     upravo
    0.59
    이자
    0.57
    也是
    0.57
     überhaupt
    0.55
    であり
    0.52
     ever
    0.52
    Activations Density 0.329%

    No Known Activations