© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13636
    Prev
    Next
    INDEX
    Explanations

    bond yields

    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_7_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
    ya
    2.72
    YA
    2.51
    入手
    2.51
    퓨
    2.40
    ov
    2.31
    heres
    2.23
    ́
    2.22
    off
    2.22
    Disposable
    2.21
    ं
    2.18
    POSITIVE LOGITS
    ICIENCY
    2.88
    𝑒
    2.80
    rd
    2.75
    धर
    2.71
    nemouth
    2.69
    वीं
    2.68
    smallskip
    2.66
    ranged
    2.64
    nnnn
    2.62
    Spoiler
    2.60
    Activations Density 0.003%

    No Known Activations