© 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. 115244
    Prev
    Next
    INDEX
    Explanations

    Singapore and Asia

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

    Singapore, highly developed Asian locations

    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
    哠
    0.54
     Marquette
    0.53
     θεω
    0.52
     Statewide
    0.52
    筮
    0.52
     parish
    0.51
     Parish
    0.51
     parishioners
    0.51
     числі
    0.51
    ⵔ
    0.50
    POSITIVE LOGITS
     Singapore
    1.40
    Asian
    1.38
    Singapore
    1.37
     Asian
    1.34
    Asia
    1.33
     Asia
    1.30
     ASEAN
    1.30
    アジア
    1.22
     Malaysian
    1.20
     Malaysia
    1.20
    Activations Density 0.129%

    No Known Activations