© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 589
    Prev
    Next
    INDEX
    Explanations

    who+auxiliary verb

    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
    𝐥
    2.17
    𝐭
    2.15
    اً
    2.05
    𝐚
    1.91
    lasses
    1.89
    𝐡
    1.83
    𝐮
    1.78
    бора
    1.78
    tr
    1.73
    𝐫
    1.72
    POSITIVE LOGITS
    트워크
    1.90
    맛
    1.87
    peh
    1.87
    _{+}$
    1.86
    τζ
    1.85
    蔘
    1.84
    ﮕ
    1.82
    oting
    1.82
     වෙත
    1.82
    톨
    1.80
    Activations Density 1.082%

    No Known Activations