© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1428
    Prev
    Next
    INDEX
    Explanations

    loss, illness, sheet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     પો
    1.08
     וו
    1.03
     Saeed
    0.97
     જા
    0.97
     衣
    0.96
     Poster
    0.95
    <unused2134>
    0.94
     酒
    0.93
     deo
    0.93
     Tiến
    0.91
    POSITIVE LOGITS
    3
    1.94
    6
    1.92
    5
    1.92
    2
    1.86
    4
    1.85
    7
    1.85
    8
    1.81
    9
    1.75
    1
    1.54
    0
    1.38
    Activations Density 0.291%

    No Known Activations