© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 53758
    Prev
    Next
    INDEX
    Explanations

    occupy space

    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_40_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
    辋
    0.41
    Underv
    0.38
    ayama
    0.37
     suffis
    0.37
    achery
    0.37
    érêt
    0.36
     emptied
    0.36
     Hàm
    0.36
    麟
    0.36
    富士
    0.35
    POSITIVE LOGITS
     occupying
    1.92
     occupy
    1.88
     occupies
    1.87
     ocupar
    1.74
     ocupa
    1.73
     ocup
    1.67
     занимает
    1.66
    占
    1.64
    佔
    1.64
     occup
    1.60
    Activations Density 0.080%

    No Known Activations