© 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. 117643
    Prev
    Next
    INDEX
    Explanations

    WATERdegradationpollutant

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

    quantities, commonality, or operations

    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
    豢
    0.46
     theſe
    0.44
     licha
    0.44
     Similarly
    0.43
     परिस्थिती
    0.41
    蓄
    0.41
    佑
    0.41
    齟
    0.41
    ဦ
    0.40
     thofe
    0.40
    POSITIVE LOGITS
    WATER
    0.48
     ಗ್ರಾಮ
    0.47
    wasser
    0.46
     degradation
    0.45
     Peak
    0.45
    Θ
    0.45
     pollutant
    0.44
     ブラ
    0.44
     ताम
    0.43
    BREAK
    0.43
    Activations Density 0.001%

    No Known Activations