© 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. 10260
    Prev
    Next
    INDEX
    Explanations

    places and locations

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

    places and locations

    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
     Callable
    0.48
    രായ
    0.47
     conseguiu
    0.45
     Manajemen
    0.44
    菈
    0.44
     luciferase
    0.43
    仡
    0.42
     figlio
    0.42
     sii
    0.42
     বিদ্ব
    0.41
    POSITIVE LOGITS
     outskirts
    0.95
     workplaces
    0.95
     luoghi
    0.94
     places
    0.92
     endroits
    0.91
     곳
    0.89
     elsewhere
    0.88
     suburbs
    0.88
     lugares
    0.85
     campuses
    0.85
    Activations Density 0.249%

    No Known Activations