© 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. 2699
    Prev
    Next
    INDEX
    Explanations

    numbers followed by nouns

    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
    ت
    2.88
    𝑎
    2.71
    т
    2.48
    د
    2.43
    ください
    2.24
     ίδ
    2.13
     espos
    2.13
    isub
    2.12
    rangea
    2.11
     riserv
    2.08
    POSITIVE LOGITS
    ième
    2.26
    Cedar
    2.25
    メートル
    2.18
    lighter
    2.13
     thousand
    2.13
    ется
    2.10
    م
    2.10
     unset
    2.10
     PHOTOS
    2.06
    у
    2.06
    Activations Density 0.109%

    No Known Activations