© 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. 71482
    Prev
    Next
    INDEX
    Explanations

    fog, mist, visibility

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

    fog, mist, 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-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
    耑
    0.52
    សូម
    0.48
     सचिव
    0.41
     ofert
    0.40
     झेल
    0.40
    紥
    0.40
     Министерства
    0.39
    ຂໍ
    0.39
    ல்ப
    0.38
    ResponseMessage
    0.38
    POSITIVE LOGITS
     foggy
    1.01
     fog
    0.94
     Visibility
    0.92
     visibility
    0.89
     Fog
    0.89
     blindness
    0.88
    雾
    0.84
    Fog
    0.84
    霧
    0.81
     Blind
    0.81
    Activations Density 0.080%

    No Known Activations