© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2543
    Prev
    Next
    INDEX
    Explanations

    come + preposition/particle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    NER
    0.72
     permanec
    0.70
     pomiesz
    0.70
     permanecer
    0.68
     Cite
    0.67
    帑
    0.67
     immovable
    0.67
    WR
    0.67
    ಖ
    0.66
     heathen
    0.66
    POSITIVE LOGITS
     crashing
    1.14
     alive
    1.12
     knocking
    1.06
    upp
    1.03
     together
    1.00
    alive
    1.00
     Alive
    0.98
    不及
    0.94
     roaring
    0.94
     tumbling
    0.92
    Activations Density 0.195%

    No Known Activations