© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10773
    Prev
    Next
    INDEX
    Explanations

    ipywidgets, secrets, voluntary

    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
    nty
    2.93
    े
    2.91
    nd
    2.88
    eppo
    2.44
    ddar
    2.41
    ndet
    2.41
    जीशन
    2.41
    र्फ
    2.32
    oMatrix
    2.31
    dest
    2.29
    POSITIVE LOGITS
    。"
    3.01
    u
    2.94
    ,"
    2.93
     ?"
    2.78
    ："
    2.69
    "]/
    2.67
    𝙩
    2.66
    :"
    2.66
    ."'
    2.65
     cộng
    2.65
    Activations Density 0.012%

    No Known Activations