© 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-16K
    7. 8763
    Prev
    Next
    INDEX
    Explanations

    you'll likely find

    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_16k_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
     usaha
    1.19
     있었
    1.19
     determinadas
    1.15
     کردیا
    1.15
     aconte
    1.13
     했
    1.11
     考え
    1.11
     일을
    1.11
     genomen
    1.09
     کرل
    1.09
    POSITIVE LOGITS
    oga
    1.03
    avg
    1.02
    opy
    1.00
    iku
    0.97
    rich
    0.96
    ahiya
    0.95
    晋
    0.95
    晉
    0.94
    uka
    0.94
    ган
    0.90
    Activations Density 0.153%

    No Known Activations