© 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. 13222
    Prev
    Next
    INDEX
    Explanations

    consumer electronics

    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
     이러한
    1.50
    톡
    1.42
     而且
    1.39
     주로
    1.39
     곡
    1.37
     수업
    1.36
     석
    1.35
     除了
    1.34
     학
    1.33
     tồn
    1.32
    POSITIVE LOGITS
    ложи
    1.37
    Control
    1.35
    ellas
    1.32
    тали
    1.30
    लिये
    1.26
    𝐬
    1.24
    Famil
    1.24
    Keller
    1.23
    Золо
    1.23
    andolo
    1.22
    Activations Density 1.510%

    No Known Activations