© 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. 128587
    Prev
    Next
    INDEX
    Explanations

    regional localisation

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

    reduced effectiveness or activity

    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
    同时也
    0.47
    hui
    0.45
     Μ
    0.44
     sekaligus
    0.44
    -',
    0.44
     "",
    0.44
    >,
    0.43
     Feminist
    0.43
     heißt
    0.43
     °,
    0.43
    POSITIVE LOGITS
     지역
    0.61
    지역
    0.51
    regional
    0.50
    localisation
    0.48
     운
    0.47
    onych
    0.47
    centroids
    0.47
    区域
    0.46
     नहर
    0.46
     ರಲ್ಲಿ
    0.46
    Activations Density 0.000%

    No Known Activations