© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 1018
    Prev
    Next
    INDEX
    Explanations

    sports teams, places, universities

    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
     sculpt
    1.31
    ometry
    1.20
     humus
    1.09
     festive
    1.08
    )]^{
    1.07
     biosphere
    1.06
     kosm
    1.06
     exempl
    1.05
     harn
    1.04
     wares
    1.04
    POSITIVE LOGITS
    niji
    1.29
    க
    1.26
     menghad
    1.22
    n
    1.22
     понимают
    1.21
    tama
    1.20
    isesti
    1.19
     الأمريكية
    1.18
     altro
    1.18
    队
    1.16
    Activations Density 0.094%

    No Known Activations