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. 47291
    Prev
    Next
    INDEX
    Explanations

    Internal advantages

    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
    quinazolin
    0.96
     особо
    0.94
     Sultan
    0.94
    hafte
    0.89
     znaj
    0.85
    ія
    0.83
    床
    0.83
    ความเป็น
    0.82
    рама
    0.82
    ుల
    0.81
    POSITIVE LOGITS
     countrymen
    1.19
     rejoicing
    1.10
    ਓ
    1.08
     revisiting
    1.07
    ционной
    1.04
     forgetting
    1.02
    ਗਾ
    1.01
     rethinking
    1.01
     godine
    1.01
     updated
    1.00
    Activations Density 0.003%

    No Known Activations