© 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. 1097
    Prev
    Next
    INDEX
    Explanations

    project manager

    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
    iyati
    2.10
    碍
    2.10
    weh
    2.05
    礙
    2.03
    erapeut
    2.03
    temperatur
    2.03
    meck
    1.99
    __,
    1.99
    ehir
    1.96
    addSubview
    1.96
    POSITIVE LOGITS
    ⎢
    2.78
    <bos>
    2.68
    ic
    2.52
    ките
    2.50
    漑
    2.41
    勰
    2.36
    惭
    2.33
    ϲ
    2.30
    凿
    2.28
    ibusdam
    2.25
    Activations Density 0.870%

    No Known Activations