© 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-65K
    7. 61512
    Prev
    Next
    INDEX
    Explanations

    regional and hospital

    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_65k_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
     суб
    0.55
     छंद
    0.53
    ลอง
    0.53
     दिव
    0.53
    𝟎
    0.53
     Това
    0.52
    𝔯
    0.51
     दुकानों
    0.50
    ショップ
    0.50
     ако
    0.50
    POSITIVE LOGITS
     Regional
    0.45
     Young
    0.44
     tart
    0.44
     hospital
    0.43
     regional
    0.43
     Reset
    0.42
    3
    0.42
     resident
    0.41
     Shank
    0.41
     Hospital
    0.41
    Activations Density 0.009%

    No Known Activations