© 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. 11431
    Prev
    Next
    INDEX
    Explanations

    company names and structures

    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
    𝗻
    2.03
     neoliberal
    2.00
     ovlád
    1.95
    ্যান্ড
    1.95
     Issa
    1.91
    চনার
    1.89
     Indeed
    1.88
     performans
    1.84
     Vista
    1.84
    Oku
    1.81
    POSITIVE LOGITS
    gif
    1.51
     symbols
    1.51
    inous
    1.50
    <bos>
    1.48
    oxides
    1.47
     tho
    1.42
     대상으로
    1.39
     treat
    1.37
    tegr
    1.37
    ாக்கு
    1.36
    Activations Density 0.015%

    No Known Activations