© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129150
    Prev
    Next
    INDEX
    Explanations

    television viewing

    np_acts-logits-general · gemini-2.5-flash-lite

    preposition followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    沏
    0.49
     উল্লেখিত
    0.49
     echte
    0.47
     мело
    0.46
    ෲ
    0.46
    ंचं
    0.45
     lớ
    0.45
    សម្រាប់ការ
    0.44
    娃
    0.44
    ফার
    0.43
    POSITIVE LOGITS
     fortuit
    0.42
    zu
    0.41
    Television
    0.40
    भाग्य
    0.40
    sey
    0.39
    sé
    0.39
     television
    0.38
    Ve
    0.38
    FileDialog
    0.38
    Editar
    0.38
    Activations Density 0.001%

    No Known Activations