Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 266
    Prev
    Next
    INDEX
    Explanations

    chatgpt or chatbot

    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_22_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
     true
    1.18
    親
    1.05
    orative
    1.04
     chief
    1.03
     исти
    1.00
     regenerated
    0.99
     Chief
    0.98
    clearInterval
    0.94
    sure
    0.93
     complementary
    0.93
    POSITIVE LOGITS
    츰
    1.33
    gwin
    1.27
    esterol
    1.25
    तुरंग
    1.24
    munk
    1.24
    mataspid
    1.23
     graphique
    1.21
    म्पियन
    1.16
    ্যালেঞ্জ
    1.14
    lains
    1.13
    Activations Density 0.627%

    No Known Activations