© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 71800
    Prev
    Next
    INDEX
    Explanations

    climbing and ladders

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of vertical climbing and working at height, especially safety procedures, equipment, and fitness/training contexts related to those activities.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ಮಾ
    0.43
    odata
    0.43
    ຂໍ້ມ
    0.43
    データの
    0.41
    皖
    0.41
     parlement
    0.40
     rdf
    0.40
     spotify
    0.39
    ्यान
    0.39
     permitt
    0.39
    POSITIVE LOGITS
     climbers
    0.87
     Climbing
    0.87
     climber
    0.86
     climbing
    0.79
     Climb
    0.77
     climbed
    0.75
     climb
    0.74
     climbs
    0.72
    攀
    0.72
     ladders
    0.71
    Activations Density 0.065%

    No Known Activations