© 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. 22938
    Prev
    Next
    INDEX
    Explanations

    Brighton & Hove Albion locations

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

    divisibility by 13

    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
     Minnesota
    0.50
    Minnesota
    0.49
     Quân
    0.46
    <unused14>
    0.44
    <unused76>
    0.44
    Magnetic
    0.42
    朗普
    0.42
    ത്തരം
    0.41
    劉
    0.40
    Indiana
    0.40
    POSITIVE LOGITS
     Sussex
    0.62
     Brighton
    0.55
     Hove
    0.50
     Woj
    0.50
     Worthing
    0.50
     Chichester
    0.46
    湘
    0.46
     వైసీపీ
    0.46
     టీడీపీ
    0.45
     conditioning
    0.45
    Activations Density 0.039%

    No Known Activations