© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2420
    Prev
    Next
    INDEX
    Explanations

    climate change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     perasaan
    1.77
     humanity
    1.61
     eu
    1.58
    粦
    1.56
    蔔
    1.54
     altın
    1.49
     geniş
    1.46
    彠
    1.45
     titik
    1.44
     krv
    1.43
    POSITIVE LOGITS
     injustice
    1.58
     vane
    1.53
     מז
    1.52
     deduct
    1.49
     forecasting
    1.48
    ienda
    1.43
     rains
    1.42
    sol
    1.41
    ⛈
    1.40
     accepting
    1.38
    Activations Density 0.115%

    No Known Activations