© 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. 2801
    Prev
    Next
    INDEX
    Explanations

    Safety requirement, dark, inflation, 1, contened

    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
    م
    1.33
    ل
    1.31
     있습니다
    1.28
    D
    1.25
    S
    1.22
     you
    1.22
    沒有
    1.21
     S
    1.18
     Esq
    1.18
     does
    1.17
    POSITIVE LOGITS
    oretically
    1.69
    🈺
    1.26
    ObjectMapper
    1.24
    electric
    1.22
    IndexOf
    1.20
    ी
    1.16
     তথা
    1.16
    🕍
    1.16
     podríamos
    1.15
     якого
    1.12
    Activations Density 0.303%

    No Known Activations