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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 188
    Prev
    Next
    INDEX
    Explanations

    in the context of

    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_29_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
    ankind
    0.80
     عدد
    0.77
     объекта
    0.77
     ہوئی
    0.73
     개의
    0.72
     نیاز
    0.71
     returnValue
    0.70
     道
    0.70
     Plattform
    0.70
     길이
    0.70
    POSITIVE LOGITS
     midst
    2.16
     meantime
    1.99
     vicinity
    1.74
     وفي
    1.42
     guise
    1.37
     middle
    1.35
     forefront
    1.28
     wake
    1.28
     absence
    1.24
     context
    1.23
    Activations Density 0.442%

    No Known Activations