© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8703
    Prev
    Next
    INDEX
    Explanations

    Case study or transaction properties

    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_262k_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
    ی
    1.47
    iados
    1.42
    tained
    1.39
    ு
    1.37
    ে
    1.36
     fichier
    1.31
     leeft
    1.29
     spurt
    1.27
    i
    1.26
     ønsker
    1.25
    POSITIVE LOGITS
     заказ
    1.31
    RA
    1.31
    ہ
    1.31
     Venus
    1.25
     hydraz
    1.23
     dialects
    1.21
    ँग
    1.20
     hallmarks
    1.20
     GPUs
    1.20
     ATMs
    1.20
    Activations Density 0.000%

    No Known Activations