© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1811
    Prev
    Next
    INDEX
    Explanations

    Replace placeholders

    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
     dniu
    2.38
    +(\
    2.33
    日英
    2.29
     ضعف
    2.05
    yun
    2.03
    䒑
    2.02
    ร้อน
    2.01
    天才
    2.00
    踰
    1.99
    ロジー
    1.97
    POSITIVE LOGITS
    िल्
    2.36
    ें
    2.13
    ilent
    2.12
    ắt
    2.11
    icro
    2.10
     אבי
    2.08
    కీయ
    2.04
    ль
    2.04
    apatillas
    2.00
    ান্ড
    2.00
    Activations Density 0.239%

    No Known Activations