© 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. 19931
    Prev
    Next
    INDEX
    Explanations

    air pollution and particulates

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

    air pollution and quality

    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
    舢
    0.63
    结局
    0.61
    谕
    0.59
    书
    0.58
    读者
    0.54
    顾问
    0.54
    小说
    0.52
     сериа
    0.52
    诈
    0.51
    阉
    0.51
    POSITIVE LOGITS
     pollution
    1.33
     pollutant
    1.19
     smog
    1.19
     pollutants
    1.17
     प्रदूषण
    1.16
     polluted
    1.15
    pollution
    1.13
     प्रदू
    1.13
     Pollution
    1.09
     particulates
    1.06
    Activations Density 0.062%

    No Known Activations