© 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. 2078
    Prev
    Next
    INDEX
    Explanations

    solving and fixing problems

    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
    zeki
    1.11
    スプレイ
    1.10
    찡
    1.03
    த்தைச்
    1.02
    সিটি
    1.00
    等人
    0.99
    ӱ
    0.98
    걀
    0.97
     탱크
    0.97
    షే
    0.97
    POSITIVE LOGITS
     solucion
    1.72
     remed
    1.67
     satisfactor
    1.44
    困
    1.40
    之道
    1.38
    这个问题
    1.37
     remedi
    1.36
     dilemmas
    1.36
     conund
    1.34
     dilemma
    1.34
    Activations Density 0.935%

    No Known Activations