© 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. 34452
    Prev
    Next
    INDEX
    Explanations

    wind and pressure systems

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

    air circulation and pressure

    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
     Rainfall
    0.66
     rainfall
    0.64
    ⛈
    0.62
    বৃষ্টি
    0.61
     बरसात
    0.55
     mưa
    0.54
     বৃষ্টি
    0.54
     雨
    0.54
     पावसा
    0.53
    rainfall
    0.53
    POSITIVE LOGITS
    helium
    0.47
     congenial
    0.47
    luft
    0.46
     diverg
    0.45
    deficient
    0.45
    圧縮
    0.43
    疊
    0.43
     compressor
    0.42
    efficient
    0.42
    pol
    0.42
    Activations Density 0.021%

    No Known Activations