© 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. 15163
    Prev
    Next
    INDEX
    Explanations

    question/answer structures

    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
    ى
    2.34
    に
    2.21
    ও
    2.06
    ्य
    2.06
    도
    2.00
    ется
    1.97
     proporcion
    1.96
    %>%
    1.96
     calor
    1.95
     radica
    1.94
    POSITIVE LOGITS
    ي
    3.27
    i
    3.15
    e
    3.14
    an
    2.97
    ebe
    2.91
    ی
    2.90
    ت
    2.88
    iant
    2.88
    on
    2.79
    in
    2.79
    Activations Density 0.043%

    No Known Activations