© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4859
    Prev
    Next
    INDEX
    Explanations

    conjunctions introducing contrast or addition

    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
     spur
    0.95
     fame
    0.84
     поча
    0.84
    ↵
    0.83
     stres
    0.80
     vibes
    0.80
     rugged
    0.78
     enjeux
    0.78
     heat
    0.77
     molt
    0.77
    POSITIVE LOGITS
     Although
    0.88
    Although
    0.84
    此同时
    0.83
    これは
    0.82
     However
    0.79
    theless
    0.78
    攷
    0.78
    虽然
    0.78
     prilikom
    0.76
     Besides
    0.76
    Activations Density 0.037%

    No Known Activations