© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10455
    Prev
    Next
    INDEX
    Explanations

    code formatting, report, template

    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_13_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
    𝙩
    2.17
    голо
    2.10
    mailed
    2.07
     Jel
    2.06
    لكتر
    2.05
    na
    2.04
    тен
    2.02
    ្នែក
    2.01
    ই
    2.00
    گونه
    1.98
    POSITIVE LOGITS
     版
    2.09
    ewalk
    1.98
    EOF
    1.96
    empot
    1.92
    em
    1.91
    รั่ง
    1.90
    ContextCompat
    1.90
    াকুর
    1.88
    lumat
    1.88
    וחות
    1.87
    Activations Density 0.175%

    No Known Activations