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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17061
    Prev
    Next
    INDEX
    Explanations

    walking

    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_31_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
     টেব
    0.43
     dibuj
    0.41
    桌
    0.41
     table
    0.40
     tabletop
    0.40
     tavolo
    0.40
     sesión
    0.40
     কক্ষে
    0.39
     bandeja
    0.39
     playroom
    0.38
    POSITIVE LOGITS
     walking
    1.09
    Walking
    1.00
     Walking
    0.97
    🚶
    0.92
    walking
    0.89
    歩
    0.83
     walk
    0.80
     berjalan
    0.80
     walked
    0.79
    步行
    0.78
    Activations Density 0.200%

    No Known Activations