© 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. 5458
    Prev
    Next
    INDEX
    Explanations

    viewport meta tag

    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
    ेक्षित
    2.06
     כן
    2.00
    ēc
    1.98
    𝙀
    1.94
    𝙉
    1.89
    nię
    1.89
    Ｎ
    1.82
    ｎ
    1.81
    খ
    1.78
     mừng
    1.77
    POSITIVE LOGITS
    ipt
    2.20
    臾
    2.04
     march
    2.01
    cim
    1.99
    녕하
    1.95
    場合に
    1.93
    ឹ
    1.92
    ೋತಿ
    1.89
    </h4>
    1.88
    方程
    1.86
    Activations Density 0.182%

    No Known Activations