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. 17-GEMMASCOPE-2-RES-65K
    4. 47306
    Prev
    Next
    INDEX
    Explanations

    relevant goal component

    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_65k_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
     Gosudarstvennyj
    1.37
    𝘬
    1.26
    pengaruhi
    1.21
    喈
    1.21
     pihak
    1.20
     carriages
    1.19
    𝖑
    1.18
     Invisible
    1.18
     dodging
    1.18
     wiping
    1.16
    POSITIVE LOGITS
    о
    0.90
    訥
    0.87
    βα
    0.85
     deadline
    0.84
    RA
    0.81
    що
    0.80
    SO
    0.78
     moreover
    0.78
    ̀
    0.78
    排名
    0.77
    Activations Density 0.016%

    No Known Activations