© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    navigating through

    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
    upam
    1.30
    al
    1.14
    ころ
    1.12
    </td>
    1.03
     delim
    1.03
    chnik
    1.03
     Kashmir
    1.02
    olk
    1.00
    ienti
    1.00
    lop
    0.99
    POSITIVE LOGITS
    蟲
    1.98
     ব্যাকটেরিয়া
    1.89
     ViewController
    1.87
     collectionView
    1.87
    廣告
    1.87
    駛
    1.87
    虫
    1.86
     vettore
    1.84
    ứa
    1.83
     corriendo
    1.83
    Activations Density 0.052%

    No Known Activations