© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6786
    Prev
    Next
    INDEX
    Explanations

    planting, installing, clearing, construction, erecting

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

    gathering, repairing, building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    閨
    0.41
     swirl
    0.41
     osią
    0.41
    怦
    0.40
    चि
    0.39
     swirls
    0.39
     confid
    0.39
     signUp
    0.39
     جمهور
    0.39
    👛
    0.39
    POSITIVE LOGITS
     erecting
    1.45
     planting
    1.27
     erect
    1.23
     erected
    1.21
     trồng
    1.20
     clearing
    1.19
    安装
    1.17
     installing
    1.16
     설치
    1.15
     excav
    1.13
    Activations Density 0.151%

    No Known Activations