© 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. 752
    Prev
    Next
    INDEX
    Explanations

    also possible, also associated, also have

    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
    ্স
    1.66
    م
    1.56
    ই
    1.45
    ও
    1.43
    Only
    1.41
     даже
    1.39
    to
    1.36
    n
    1.34
    ্ড
    1.33
    te
    1.32
    POSITIVE LOGITS
     noteworthy
    1.93
     самое
    1.84
    तरी
    1.79
     বটে
    1.79
     notable
    1.77
     importantly
    1.72
     불구하고
    1.67
     incidentally
    1.60
    ਡੀ
    1.52
    らえる
    1.45
    Activations Density 0.114%

    No Known Activations