© 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. 672
    Prev
    Next
    INDEX
    Explanations

    descriptions of tasks and choices

    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
     sockfd
    1.26
     satisfaction
    1.24
    꿉
    1.18
    뀔
    1.15
    뀝
    1.13
    롯
    1.12
     adjudicated
    1.11
    իս
    1.11
     되겠
    1.11
    فل
    1.10
    POSITIVE LOGITS
     trang
    1.76
    Packet
    1.68
     Tape
    1.65
    >::
    1.61
     Пи
    1.60
     Packet
    1.56
    BSD
    1.55
    tape
    1.54
     Promo
    1.54
     जापान
    1.53
    Activations Density 0.000%

    No Known Activations