© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9857
    Prev
    Next
    INDEX
    Explanations

    reflecting light and emotions

    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
    લિ
    2.42
    蔫
    2.28
    getConnection
    2.24
    트워크
    2.23
    statusbar
    2.21
    datatables
    2.19
    zmdi
    2.19
    passt
    2.17
    ἲ
    2.13
    blastoma
    2.12
    POSITIVE LOGITS
    ی
    2.40
    स्त्रा
    2.21
     apropi
    2.16
    inians
    2.16
    ations
    2.15
    敤
    2.07
    ropshire
    2.05
    ânea
    2.04
     integrand
    2.02
     apropri
    2.00
    Activations Density 0.294%

    No Known Activations