© 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. 10301
    Prev
    Next
    INDEX
    Explanations

    GPT Llama numbers

    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
    க்கு
    0.76
     magically
    0.75
     Peng
    0.75
     penge
    0.75
    ′
    0.75
    ″
    0.74
     synonymous
    0.74
     Master
    0.74
     أوروب
    0.74
     literally
    0.73
    POSITIVE LOGITS
     ۳
    1.46
    4
    1.46
    ４
    1.41
    3
    1.40
     XII
    1.39
    2
    1.37
     III
    1.36
    ３
    1.35
    1
    1.35
     ۲
    1.33
    Activations Density 0.231%

    No Known Activations