© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    partnership or collaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     speechSynthesis
    0.54
     topographic
    0.52
     растя
    0.50
     topo
    0.49
    ታት
    0.49
    Percy
    0.48
    😪
    0.48
     attic
    0.48
     brows
    0.47
    🪜
    0.47
    POSITIVE LOGITS
     partnership
    3.42
     partnering
    3.27
     partenariat
    3.23
     parceria
    3.17
    partnership
    3.17
     partnerships
    3.14
     partnered
    3.13
     samarbe
    3.00
     collaboration
    2.97
     collaborations
    2.92
    Activations Density 0.917%

    No Known Activations