© 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-262K
    7. 193749
    Prev
    Next
    INDEX
    Explanations

    fog and haze

    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_262k_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
    コンビニ
    0.45
    趔
    0.45
     стаўкі
    0.45
     छंद
    0.40
    嘣
    0.40
    Cookie
    0.40
     mentors
    0.39
    cessor
    0.39
    cookie
    0.39
     मुद्रा
    0.39
    POSITIVE LOGITS
     fog
    1.88
    Fog
    1.63
     haze
    1.59
     foggy
    1.58
     Fog
    1.51
    fog
    1.50
    雾
    1.48
    霧
    1.48
     hazy
    1.35
     smog
    1.22
    Activations Density 0.045%

    No Known Activations