© 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. 14911
    Prev
    Next
    INDEX
    Explanations

    numbers and phrases

    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
     meaning
    0.64
     conven
    0.63
    isotropic
    0.62
     starring
    0.60
     normal
    0.59
     our
    0.59
    🚵
    0.59
     এমনি
    0.58
     '.
    0.58
     caric
    0.58
    POSITIVE LOGITS
    ยังมี
    0.75
    ‍♀
    0.71
    Не
    0.69
    所有
    0.69
    และ
    0.69
    ৯
    0.67
     ترتیب
    0.66
     lâng
    0.65
     abiotic
    0.64
    ්‍යා
    0.64
    Activations Density 1.215%

    No Known Activations