© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    Diffusion, damage, layers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    {
    3.21
    एस
    3.16
    𝒃
    3.12
     been
    3.08
    اء
    2.97
     direito
    2.95
    𝟏
    2.91
    doped
    2.85
     início
    2.85
    منى
    2.80
    POSITIVE LOGITS
    ية
    3.54
    м
    3.48
    र
    3.32
    ী
    3.16
    ма
    3.15
    특별시
    3.09
    il
    3.06
    酚
    3.03
    었다
    2.94
    ot
    2.89
    Activations Density 0.252%

    No Known Activations