© 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. 38082
    Prev
    Next
    INDEX
    Explanations

    cleanliness of places

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

    clean and cleanliness

    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
     scenic
    0.51
     purifying
    0.46
     purify
    0.46
    :_
    0.45
     NAVIGATION
    0.44
    वायरमेंट
    0.44
     উন্নত
    0.43
     purification
    0.43
     east
    0.43
     ages
    0.43
    POSITIVE LOGITS
    𝐅
    0.50
     Fey
    0.49
    可靠
    0.48
     starost
    0.47
    liness
    0.46
    рія
    0.46
     terminé
    0.46
     misfort
    0.46
     Filipp
    0.45
     Lori
    0.45
    Activations Density 0.013%

    No Known Activations