© 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. 14947
    Prev
    Next
    INDEX
    Explanations

    code initialization and conditions

    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
    颂
    0.84
     showcased
    0.79
    adden
    0.78
     โปร
    0.78
     κε
    0.78
     प्ला
    0.77
    প্ল
    0.77
     హో
    0.76
    つの
    0.75
     Promotional
    0.74
    POSITIVE LOGITS
     ಹುಡು
    0.71
    мут
    0.70
    ={
    0.70
     =[
    0.70
    formula
    0.70
     prede
    0.69
     rectMode
    0.69
    साय
    0.64
    calcul
    0.64
    ="(
    0.64
    Activations Density 0.212%

    No Known Activations