© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    how to do something using

    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
    setzung
    1.59
     construcción
    1.52
     rozwoju
    1.45
     لت
    1.44
    对于
    1.41
    對於
    1.39
     kısmı
    1.38
     razvoja
    1.37
    ்க்
    1.36
    に
    1.35
    POSITIVE LOGITS
    %%
    1.14
    ines
    1.11
    polyfill
    1.11
    ipherals
    1.09
    ので
    1.08
    0
    1.07
    without
    1.05
     freely
    1.03
     unmodified
    1.01
     pliers
    1.00
    Activations Density 0.589%

    No Known Activations