© 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. 12974
    Prev
    Next
    INDEX
    Explanations

    sarcasm or multilingualism

    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
     Observable
    2.59
     convi
    2.54
    Cadastro
    2.52
    ╕
    2.46
    טר
    2.43
    ದ
    2.42
     borrow
    2.40
    Agregar
    2.38
     interesar
    2.35
     entitle
    2.33
    POSITIVE LOGITS
    a
    2.85
    assertEqual
    2.58
    olgens
    2.49
    etica
    2.47
    țiile
    2.43
    ohyd
    2.40
    ovenants
    2.39
    ţiile
    2.39
    ྤ
    2.35
     ஆண்டுகளுக்கு
    2.32
    Activations Density 0.015%

    No Known Activations