© 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. 9675
    Prev
    Next
    INDEX
    Explanations

    988

    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
    ////////////////
    2.45
    UTURE
    2.41
    ֒
    2.36
    🖉
    2.32
    𝑠
    2.30
    𝑢
    2.29
    ্লেখ
    2.28
    ExtensionsPath
    2.24
    assembling
    2.17
    פּ
    2.15
    POSITIVE LOGITS
    <bos>
    2.69
    er
    2.17
    erah
    2.09
    erat
    1.96
    ceived
    1.93
     direct
    1.91
    kingen
    1.88
    erar
    1.88
    erin
    1.87
    िंग
    1.85
    Activations Density 0.084%

    No Known Activations