© 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. 9691
    Prev
    Next
    INDEX
    Explanations

    4x or 4+

    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
    কেন্ড
    3.92
    ৯
    3.80
    QtWidgets
    3.41
     translateY
    3.22
    ৯০
    3.20
    できるよう
    3.13
    𝚊
    2.97
    ال
    2.91
     SQLException
    2.83
    ৯৫
    2.83
    POSITIVE LOGITS
     dioxane
    4.43
    ঠা
    3.88
     quadrants
    3.81
    fifths
    3.76
    ا
    3.75
     cinqui
    3.19
    مح
    3.15
    는
    3.15
    कोल
    3.15
    cerr
    3.07
    Activations Density 0.523%

    No Known Activations