© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15487
    Prev
    Next
    INDEX
    Explanations

    data cleaning

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     apk
    0.57
     conférence
    0.56
    ジェル
    0.54
    可爱
    0.53
    ControlButton
    0.53
     lettre
    0.53
    indoor
    0.53
    +(\
    0.52
     conférences
    0.52
    iros
    0.52
    POSITIVE LOGITS
     cleansed
    1.37
     cleansing
    1.33
     cleanse
    1.31
     metadata
    1.20
     ETL
    1.20
     Metadata
    1.16
     Extract
    1.13
     ingestion
    1.13
     normalization
    1.12
     extraction
    1.10
    Activations Density 0.132%

    No Known Activations