© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5886
    Prev
    Next
    INDEX
    Explanations

    dimensional arrays and graphics

    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_17_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
     innego
    1.20
     otra
    1.13
     clase
    1.09
     otro
    1.09
     afirm
    1.08
    劲
    1.08
    一场
    1.06
     basta
    1.05
     transcend
    1.04
     gente
    1.03
    POSITIVE LOGITS
    iation
    1.29
    ى
    1.28
    ности
    1.28
    ism
    1.27
    ність
    1.27
    чины
    1.27
    TEMPLATE
    1.23
    手術
    1.19
    Natal
    1.19
    ness
    1.18
    Activations Density 0.247%

    No Known Activations