© 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. 40-GEMMASCOPE-2-RES-65K
    7. 50630
    Prev
    Next
    INDEX
    Explanations

    vertical movement upwards

    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
    Jump
    0.50
     jumps
    0.49
     terbang
    0.46
    뛴
    0.45
     leapt
    0.45
    jump
    0.44
    uszcz
    0.43
     nhảy
    0.43
    飛
    0.42
    jumpa
    0.42
    POSITIVE LOGITS
     climbing
    0.54
    爬
    0.54
     frame
    0.52
     crawl
    0.52
     stairs
    0.50
     crawling
    0.48
     staircase
    0.48
     climbed
    0.48
     climb
    0.47
     climbs
    0.47
    Activations Density 0.013%

    No Known Activations