© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11132
    Prev
    Next
    INDEX
    Explanations

    tell me your location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಪುಸ್ತಕ
    0.57
     metabolized
    0.52
    分裂
    0.50
     書い
    0.49
     kože
    0.48
     chronique
    0.47
    代谢
    0.47
    🎀
    0.47
     δημιουργ
    0.46
     žmog
    0.46
    POSITIVE LOGITS
     location
    0.82
     Location
    0.77
     confirm
    0.72
     postcode
    0.72
     locations
    0.71
    Location
    0.68
     locate
    0.67
    location
    0.64
     choose
    0.63
     lokasi
    0.63
    Activations Density 0.002%

    No Known Activations