© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10130
    Prev
    Next
    INDEX
    Explanations

    confirming understanding or finality

    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
     dint
    1.54
    ように
    1.49
    ল
    1.41
    Resizable
    1.32
    iful
    1.30
    yy
    1.29
    ument
    1.21
    uin
    1.19
    Collider
    1.19
    yyyy
    1.18
    POSITIVE LOGITS
     встречи
    1.50
    
    1.44
     встре
    1.42
     Зна
    1.39
     подачи
    1.37
    知道
    1.37
     availability
    1.37
     notifications
    1.36
     emergence
    1.36
    sklär
    1.35
    Activations Density 0.008%

    No Known Activations