© 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. 2843
    Prev
    Next
    INDEX
    Explanations

    numbers and names in lists

    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
     facet
    1.25
     поверхность
    1.24
     commutative
    1.21
     तो
    1.10
     aandacht
    1.10
     العلم
    1.08
    슥
    1.06
    ر
    1.05
     adequado
    1.01
    Bigg
    1.00
    POSITIVE LOGITS
     renovated
    1.32
    ous
    1.31
     amalgamated
    1.29
     ravaged
    1.28
    etiti
    1.27
     vener
    1.24
    )}=
    1.23
    weds
    1.23
     depicts
    1.20
    theless
    1.20
    Activations Density 0.244%

    No Known Activations