© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14044
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts and functions

    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
    $)$.
    2.48
     displaying
    2.23
     взрос
    2.20
     भीड़
    2.06
    junit
    2.06
    ïne
    2.04
    ysuckle
    2.02
    LLER
    1.99
     Adult
    1.96
    жали
    1.96
    POSITIVE LOGITS
    wechsl
    2.49
    徴
    2.29
    uruhan
    2.28
    呲
    2.24
    ொ
    2.24
    ्यास
    2.22
    ധിപ
    2.22
    isten
    2.17
    ै
    2.16
    f
    2.15
    Activations Density 0.009%

    No Known Activations