© 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. 32028
    Prev
    Next
    INDEX
    Explanations

    Scotland and its cities

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

    Scotland, Edinburgh, sqlite

    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
     Xu
    0.52
    螻
    0.47
    洩
    0.45
    嘮
    0.44
     Vortex
    0.44
    複合
    0.44
    滁
    0.44
    汪
    0.43
    蘆
    0.43
    uesto
    0.41
    POSITIVE LOGITS
     Scotland
    1.60
    Scotland
    1.54
     Scottish
    1.50
     scottish
    1.45
    Scottish
    1.42
    Glasgow
    1.30
     Edinburgh
    1.28
     Glasgow
    1.26
     Scots
    1.23
    Edinburgh
    1.21
    Activations Density 0.164%

    No Known Activations