© 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. 209
    Prev
    Next
    INDEX
    Explanations

    number 2

    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
     thirteen
    0.93
     triplets
    0.92
     triple
    0.87
     Thirteen
    0.85
     sevent
    0.85
    
    0.84
     seventh
    0.84
     siete
    0.82
     Triple
    0.82
     fifth
    0.81
    POSITIVE LOGITS
    2
    3.31
    ２
    2.91
     ۲
    2.79
    ۲
    2.75
     ٢
    2.75
    ٢
    2.67
    २
    2.65
     २
    2.61
    ২
    2.51
     ૨
    2.48
    Activations Density 3.344%

    No Known Activations