© 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. 612
    Prev
    Next
    INDEX
    Explanations

    listing pros and cons

    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
     ο
    2.09
     συ
    2.07
     լ
    1.96
     զ
    1.93
     preserve
    1.92
     handleDelete
    1.90
     getNodeId
    1.88
     Ο
    1.87
     πολύ
    1.86
     Ι
    1.85
    POSITIVE LOGITS
    and
    1.65
    <end_of_image>
    1.55
    a
    1.54
    <h2>
    1.51
    ،
    1.45
    iki
    1.45
    Gambar
    1.45
    ako
    1.44
    <h3>
    1.41
    aka
    1.41
    Activations Density 0.703%

    No Known Activations