© 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. 16332
    Prev
    Next
    INDEX
    Explanations

    industrial chemical plants and material production

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

    cryogenic industrial processes

    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
    恐惧
    0.88
    辏
    0.82
    民间
    0.81
    渐渐
    0.79
    焦虑
    0.79
    情节
    0.77
    娇
    0.77
    镜头
    0.76
    欤
    0.76
    车辆
    0.76
    POSITIVE LOGITS
     refinery
    1.17
     feedstock
    1.09
     reactor
    1.03
     wastewater
    1.02
     plant
    1.00
     reactors
    0.99
     refineries
    0.99
     cogeneration
    0.99
     effluent
    0.98
     boilers
    0.96
    Activations Density 0.135%

    No Known Activations