© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9115
    Prev
    Next
    INDEX
    Explanations

    atmospheric ozone and clouds

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

    atmospheric

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

    atmospheric

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
    泗
    0.44
    瀨
    0.43
    runoff
    0.42
    荏
    0.42
     뒷
    0.42
    pstmt
    0.41
     submer
    0.41
    锹
    0.41
    訒
    0.41
    ResultSet
    0.41
    POSITIVE LOGITS
     clouds
    1.59
     skies
    1.57
     sky
    1.56
     atmospheric
    1.49
     하늘
    1.44
     Atmospheric
    1.40
     stratosphere
    1.39
    clouds
    1.38
    atmospheric
    1.37
     langit
    1.34
    Activations Density 0.199%

    No Known Activations