© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63846
    Prev
    Next
    INDEX
    Explanations

    materials and substances

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

    materials listed in a technical context, particularly when metals and other substances are being discussed together.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metal
    -1.79
     metals
    -1.75
    金属
    -1.70
     Metals
    -1.59
    metal
    -1.54
    Metal
    -1.48
     metallic
    -1.48
     металли
    -1.45
     METAL
    -1.44
     Metal
    -1.39
    POSITIVE LOGITS
     plastic
    1.21
     wooden
    1.18
     wood
    1.18
     other
    1.09
     plastics
    1.02
     organic
    0.99
     leather
    0.94
     rubber
    0.91
    plastic
    0.90
     gemstones
    0.90
    Activations Density 0.064%

    No Known Activations