© 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. 2561
    Prev
    Next
    INDEX
    Explanations

    metals and minerals

    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
     बीबी
    0.78
     лест
    0.72
     Dwayne
    0.70
     Brentford
    0.70
     শেখ
    0.70
     पठान
    0.68
    裴
    0.65
    chai
    0.64
     سید
    0.63
    飓
    0.63
    POSITIVE LOGITS
     copper
    2.38
     Copper
    2.15
    copper
    2.14
    Copper
    2.13
     zinc
    2.09
     metals
    2.06
     cadmium
    2.03
     Zinc
    2.00
     manganese
    1.99
     nickel
    1.98
    Activations Density 0.373%

    No Known Activations