© 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. 2299
    Prev
    Next
    INDEX
    Explanations

    policy and budget

    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
    ی
    3.76
    <bos>
    3.31
    śród
    2.82
    고
    2.67
    ு
    2.65
    🅔
    2.63
    erden
    2.63
    ುಕ
    2.58
     kepentingan
    2.58
    eldorf
    2.56
    POSITIVE LOGITS
    裟
    3.58
    ्वती
    3.09
    鹉
    3.06
    ंपरा
    2.98
    ंपरिक
    2.95
    嵋
    2.87
    ওনা
    2.82
    िस्थित
    2.80
    вает
    2.80
    ্য
    2.63
    Activations Density 0.306%

    No Known Activations