© 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. 145520
    Prev
    Next
    INDEX
    Explanations

    page and location information

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

    travel and international topics

    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
    ەك
    0.42
    ’
    0.42
     nuestro
    0.42
    দিন
    0.41
     প্রসার
    0.41
    ปี
    0.40
     publica
    0.40
     উপজে
    0.40
     explicar
    0.39
    w
    0.39
    POSITIVE LOGITS
    TypeScript
    0.46
    gruppe
    0.44
     যাচ্ছিল
    0.44
    ConformanceMode
    0.44
    DownLatch
    0.43
     Timatic
    0.42
    mensagem
    0.42
    OfInterest
    0.42
     postfix
    0.41
     TypeScript
    0.41
    Activations Density 0.000%

    No Known Activations