© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    you name it

    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
    in
    1.55
    o
    1.37
    ed
    1.20
    ه
    1.14
    𝗇
    1.14
    avil
    1.14
     Tint
    1.14
    $\{
    1.12
    एशन
    1.12
    ंडर
    1.11
    POSITIVE LOGITS
     confond
    1.38
    ല
    1.24
    飨
    1.19
     throat
    1.19
    жке
    1.19
     pianta
    1.17
     ordem
    1.16
    தர
    1.15
     खुराक
    1.15
     sweeter
    1.14
    Activations Density 0.004%

    No Known Activations