© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66440
    Prev
    Next
    INDEX
    Explanations

    copper and its uses

    np_acts-logits-general · gemini-2.5-flash-lite

    copper, copper salts, copper alloys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    addena
    0.47
    ՞
    0.45
    গ্রহায়ণ
    0.44
    轲
    0.44
     săptăm
    0.44
    ringstream
    0.43
    लेखित
    0.43
     കോടതി
    0.43
    യ്‌
    0.42
     arriv
    0.42
    POSITIVE LOGITS
     copper
    1.27
     Copper
    1.17
    Copper
    1.03
    銅
    1.03
    copper
    1.02
    铜
    0.99
     cuivre
    0.89
     cobre
    0.75
     bronze
    0.73
     CuO
    0.73
    Activations Density 0.045%

    No Known Activations