© 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. 894
    Prev
    Next
    INDEX
    Explanations

    complex and varied topics

    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
     appendage
    1.49
     tangga
    1.47
     astring
    1.37
     cetera
    1.36
     egot
    1.36
    DTO
    1.36
     hoi
    1.31
    倘
    1.31
     Avengers
    1.30
     Actors
    1.30
    POSITIVE LOGITS
     προς
    1.63
     contin
    1.41
     młod
    1.31
    到了
    1.28
    പു
    1.27
    σμ
    1.26
    ydi
    1.24
    yukur
    1.24
    fromi
    1.23
     smoothly
    1.23
    Activations Density 0.000%

    No Known Activations