© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12721
    Prev
    Next
    INDEX
    Explanations

    quotes and traffic

    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
    <bos>
    3.62
     Baiklah
    2.45
     λόγω
    2.41
     cr
    2.40
    ябре
    2.37
     repeats
    2.30
    는
    2.30
    षद
    2.25
    therners
    2.23
     المثل
    2.22
    POSITIVE LOGITS
    蛳
    2.80
    ӯ
    2.78
    ッズ
    2.69
    𝗪
    2.64
     যাবত
    2.60
    មើ
    2.52
    iyu
    2.50
    gbm
    2.49
    ენ
    2.49
    इक
    2.48
    Activations Density 0.012%

    No Known Activations