© 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. 40521
    Prev
    Next
    INDEX
    Explanations

    smartphone or mobile device

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

    smartphone and laptop usage

    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
     necrosis
    0.44
     anti
    0.43
     "_
    0.42
     annihilation
    0.42
    splitext
    0.42
    เกม
    0.41
     hydraz
    0.41
    篆
    0.41
    ভূত
    0.41
     chống
    0.41
    POSITIVE LOGITS
     smartphone
    0.94
     Smartphone
    0.91
     Smartphones
    0.90
     смартфо
    0.89
     смартфон
    0.88
     smartphones
    0.87
    smartphone
    0.85
     Laptop
    0.82
     iPhones
    0.81
    スマートフォン
    0.80
    Activations Density 0.108%

    No Known Activations