© 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. 11024
    Prev
    Next
    INDEX
    Explanations

    sed command usage

    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
    elő
    2.81
    กำ
    2.81
    ํา
    2.67
    có
    2.66
    nú
    2.60
    ++',
    2.59
    نى
    2.43
    lihat
    2.40
    tanggal
    2.38
    iamen
    2.36
    POSITIVE LOGITS
     $(".
    2.18
     [{"
    2.17
    pti
    2.16
    Dg
    2.16
    ভাবে
    2.13
    prise
    2.08
    Fare
    2.00
     defineConfig
    1.98
    wna
    1.97
    <tr>
    1.97
    Activations Density 0.001%

    No Known Activations