© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8667
    Prev
    Next
    INDEX
    Explanations

    flood and flooding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     धूल
    0.52
    原子
    0.45
     chilled
    0.43
     polvo
    0.43
    🚬
    0.43
     vitamina
    0.43
     dusted
    0.42
     Dust
    0.41
    樺
    0.41
     decoración
    0.40
    POSITIVE LOGITS
     flooded
    2.00
     flooding
    1.98
     flood
    1.88
     inund
    1.76
     floods
    1.71
    Flood
    1.71
    flood
    1.64
     Flood
    1.59
     बाढ़
    1.51
     banjir
    1.47
    Activations Density 0.231%

    No Known Activations