© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    out followed by particles

    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
    &=\
    1.17
    к
    1.15
    нт
    1.10
    ajas
    1.10
    ficha
    1.10
     যুক্তরাষ্ট্রে
    1.08
     রাজাকার
    1.08
    噫
    1.08
    fem
    1.07
     evidente
    1.05
    POSITIVE LOGITS
    ात
    1.05
    shore
    1.05
    ності
    1.00
    credits
    0.97
    side
    0.96
    ात्
    0.95
    வற்றை
    0.94
    valued
    0.90
    配列
    0.90
    鹉
    0.90
    Activations Density 0.001%

    No Known Activations