© 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. 76689
    Prev
    Next
    INDEX
    Explanations

    arrested or located

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

    location / where

    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
    嫒
    0.46
    ंशी
    0.43
     туда
    0.43
    摻
    0.41
     குழந்தை
    0.41
    攙
    0.41
    GTUIKit
    0.41
    𝑌
    0.40
    ﺛ
    0.40
    CTOGRAM
    0.38
    POSITIVE LOGITS
     located
    1.69
    located
    1.56
     Located
    1.55
    位于
    1.46
    Located
    1.41
     ubicado
    1.36
    位於
    1.32
     ubicada
    1.30
     situé
    1.22
     Location
    1.21
    Activations Density 1.050%

    No Known Activations