© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15329
    Prev
    Next
    INDEX
    Explanations

    cleaning and cleanliness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    EditDialogOpen
    1.61
    ди
    1.60
     least
    1.60
    ок
    1.57
    dehyde
    1.56
    𝒐
    1.55
    guessed
    1.54
     accent
    1.54
    ᑎ
    1.52
    izzate
    1.49
    POSITIVE LOGITS
    liness
    2.40
    🧼
    2.03
     scour
    1.97
     sạch
    1.87
     nettoyage
    1.82
     slate
    1.70
     cleans
    1.64
     limpieza
    1.63
    涤
    1.60
    掃除
    1.59
    Activations Density 0.193%

    No Known Activations