© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1031
    Prev
    Next
    INDEX
    Explanations

    industrial products and machinery

    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_16k_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
     паліты
    0.84
    统治
    0.83
     політи
    0.82
     полити
    0.79
    批评
    0.78
    辩
    0.77
    变革
    0.77
    谴
    0.77
    剧情
    0.75
    危机
    0.74
    POSITIVE LOGITS
     products
    0.95
     factory
    0.91
     product
    0.86
     RoHS
    0.86
     ultrasonic
    0.86
     brushless
    0.85
     LED
    0.82
     manufacturers
    0.81
     OEM
    0.81
     industrial
    0.80
    Activations Density 0.111%

    No Known Activations