© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6123
    Prev
    Next
    INDEX
    Explanations

    drawing instructions or ui elements

    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
    PropertyParam
    0.82
     meteor
    0.82
     meteorological
    0.78
     ге
    0.78
     преду
    0.78
     gleaned
    0.78
     inesper
    0.78
    
    0.77
     университе
    0.76
     veroor
    0.76
    POSITIVE LOGITS
    Container
    0.74
    Sequence
    0.69
    Remove
    0.68
    Shared
    0.68
     dividing
    0.68
     Surrounded
    0.67
     compartments
    0.66
    Deck
    0.66
     Container
    0.66
    removeAll
    0.65
    Activations Density 0.130%

    No Known Activations