© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2889
    Prev
    Next
    INDEX
    Explanations

    datasetRoot Datasetadjacency matrix

    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
     deg
    0.80
     sin
    0.69
     decon
    0.68
    fraction
    0.68
     divisional
    0.68
     nw
    0.67
    argc
    0.67
     x
    0.66
     जायेगा
    0.65
     प्रश्
    0.65
    POSITIVE LOGITS
    mathcal
    1.57
     dataset
    1.34
    Dataset
    1.24
     Dataset
    1.22
    dataset
    1.19
    mathscr
    1.15
     datasets
    1.02
    mathbb
    0.95
    Datasets
    0.87
     DataSet
    0.86
    Activations Density 0.112%

    No Known Activations