© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2854
    Prev
    Next
    INDEX
    Explanations

    resources for help

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ں
    1.61
     قدیم
    1.53
    ষ্ঠ
    1.53
     Upcoming
    1.51
     изпъл
    1.49
     réessayer
    1.49
    此
    1.47
    𝓸
    1.46
    usalem
    1.43
    و
    1.43
    POSITIVE LOGITS
    ﻪ
    2.30
    ﺔ
    1.99
    علم
    1.92
    executor
    1.90
     BrowserModule
    1.71
    鸯
    1.70
    ومن
    1.69
     vouch
    1.69
    कर्णी
    1.67
    schema
    1.66
    Activations Density 0.079%

    No Known Activations