© 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. 106549
    Prev
    Next
    INDEX
    Explanations

    retail and commercial locations

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

    maps terms to documents

    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
    ணை
    0.52
     ಅಥವಾ
    0.50
     ئۇ
    0.49
    Შ
    0.48
    ²/
    0.48
    ணுவ
    0.48
    حديد
    0.47
     wodurch
    0.46
    PrimaryKey
    0.46
    推定
    0.44
    POSITIVE LOGITS
     showrooms
    0.56
    k
    0.48
     p
    0.46
    ют
    0.46
     beaches
    0.46
     by
    0.45
    oe
    0.44
     boutiques
    0.44
    s
    0.43
     annivers
    0.42
    Activations Density 0.001%

    No Known Activations