© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4049
    Prev
    Next
    INDEX
    Explanations

    "2023/2024"

    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_65k_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
    两
    0.81
    
    0.81
    兩
    0.80
    兩
    0.80
     ૧
    0.80
     ۲۰۱
    0.77
     ২০১৭
    0.76
     ၁
    0.76
    
    0.76
    ToJava
    0.75
    POSITIVE LOGITS
    🫡
    0.74
    অধ
    0.72
    supabase
    0.72
    🫢
    0.69
    ২৪
    0.68
     streamer
    0.64
    🫶
    0.64
     ча
    0.64
    🫰
    0.63
    ܚ
    0.63
    Activations Density 0.058%

    No Known Activations