© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 9965
    Prev
    Next
    INDEX
    Explanations

    Chemical: reactions, industry, structure, burns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ु
    2.05
    ים
    2.02
     microwave
    1.89
     symbolizes
    1.83
    NING
    1.81
     symbolize
    1.78
     apologized
    1.77
     oxidized
    1.69
    és
    1.68
     alluded
    1.66
    POSITIVE LOGITS
    ب
    2.58
     веществ
    2.31
    ﻤ
    2.25
    ﻮ
    2.17
    ﺒ
    2.02
    ﺸ
    2.02
    ভাবে
    1.99
    не
    1.87
    τερα
    1.81
    器
    1.80
    Activations Density 0.045%

    No Known Activations