© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5337
    Prev
    Next
    INDEX
    Explanations

    go to

    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
    Ș
    1.31
     Ș
    1.25
     Vý
    1.22
    Vý
    1.20
     Kā
    1.18
    ITÉ
    1.14
    Ț
    1.12
    ții
    1.12
     أيضًا
    1.11
     Ō
    1.09
    POSITIVE LOGITS
     equipments
    1.15
     loosing
    1.14
     আরম্ভ
    1.13
     accomplishment
    1.02
     bunch
    1.01
     evidences
    1.01
     advices
    1.01
     midst
    0.98
     own
    0.95
     lately
    0.94
    Activations Density 0.005%

    No Known Activations