© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3495
    Prev
    Next
    INDEX
    Explanations

    steps for running code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     @
    0.89
     ;;
    0.84
    const
    0.83
    instagram
    0.80
     Teens
    0.79
    graphql
    0.75
     তৃতীয়
    0.75
     gorgeous
    0.74
     दुसरे
    0.74
     Settlements
    0.73
    POSITIVE LOGITS
    
    0.68
    බ්
    0.64
    elope
    0.64
     poważ
    0.62
    Downloaded
    0.62
     lớn
    0.62
     approached
    0.61
    ⴻ
    0.61
     подачи
    0.61
    accio
    0.60
    Activations Density 0.020%

    No Known Activations