© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14193
    Prev
    Next
    INDEX
    Explanations

    plastic and polypropylene

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    诗
    0.50
     철
    0.48
    汉
    0.47
    spacePad
    0.46
    铁
    0.46
    Agen
    0.46
     病
    0.45
    痹
    0.45
    ငံ
    0.45
     آهن
    0.45
    POSITIVE LOGITS
     plastic
    1.31
     plastics
    1.19
     thermoplastic
    1.14
     thermoplastics
    1.14
     plástico
    1.06
    plastic
    1.03
     polyethylene
    1.03
     Plastics
    1.03
     Plastic
    1.02
     प्लास्टिक
    1.01
    Activations Density 0.057%

    No Known Activations