© 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. 2770
    Prev
    Next
    INDEX
    Explanations

    natural phenomena, talent, sounds, element, properties

    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
    ب
    4.54
    en
    4.06
    i
    3.50
    क
    3.42
    м
    3.35
    <0xC4>
    3.24
    ographic
    3.07
    و
    3.02
    ি
    2.92
    ി
    2.87
    POSITIVE LOGITS
    اً
    3.71
    quoi
    3.52
    ्य
    3.29
    ية
    3.24
    bbene
    3.19
    عة
    3.09
     уж
    3.08
    лся
    2.98
    ных
    2.98
    ется
    2.94
    Activations Density 0.281%

    No Known Activations