© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41869
    Prev
    Next
    INDEX
    Explanations

    questions about personal life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -1.22
    其
    -1.15
     kanilang
    -1.12
    夘
    -1.12
    weds
    -1.09
    ﺟ
    -1.09
    その
    -1.09
     pagado
    -1.07
    foundland
    -1.06
     referirse
    -1.05
    POSITIVE LOGITS
     at
    1.77
    rijving
    1.23
     under
    1.13
    ไม่มี
    1.11
     alebo
    1.08
    😝
    1.08
     שלך
    1.07
    :
    1.06
     jika
    1.05
     sekarang
    1.05
    Activations Density 0.073%

    No Known Activations