© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 62572
    Prev
    Next
    INDEX
    Explanations

    walking paths and routes

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     foggy
    0.43
     moist
    0.40
    ORTYPE
    0.40
    ínű
    0.39
     screech
    0.38
    ِل
    0.38
     moistened
    0.38
     ascended
    0.38
    廠
    0.38
    اهر
    0.37
    POSITIVE LOGITS
     trail
    0.71
    Trail
    0.65
     footpath
    0.65
     Trail
    0.64
    trail
    0.62
     backpacking
    0.55
     Trails
    0.54
     long
    0.53
    Way
    0.51
    걷
    0.51
    Activations Density 0.001%

    No Known Activations