© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    else or otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     fenó
    0.54
     occupies
    0.51
            
    0.50
    ด์
    0.49
    ِی
    0.48
     watts
    0.47
     públicas
    0.47
     vanadium
    0.47
     lexical
    0.47
     прямоуго
    0.47
    POSITIVE LOGITS
     else
    0.62
     Otherwise
    0.57
    else
    0.56
     Else
    0.55
    elif
    0.54
    ī
    0.51
     otherwise
    0.50
    其他
    0.50
     elsif
    0.49
    その他
    0.48
    Activations Density 0.263%

    No Known Activations