© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7632
    Prev
    Next
    INDEX
    Explanations

    `airflow info` essential information

    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
     κ
    1.05
    μά
    1.02
    ற்ற
    0.99
    ﻃ
    0.97
     දු
    0.97
    מת
    0.95
    நில
    0.95
    μα
    0.95
     মিল
    0.94
     RÉ
    0.94
    POSITIVE LOGITS
    yh
    1.24
    y
    1.15
    同时也
    1.14
     coloro
    1.09
    irikan
    1.02
    মধ্যে
    1.02
    yed
    1.00
    含有
    1.00
    ي
    0.97
    yiz
    0.97
    Activations Density 0.000%

    No Known Activations