© 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-16K
    7. 13152
    Prev
    Next
    INDEX
    Explanations

    even though, if, though, without

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

    even in contrast or exception

    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_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
    ون
    0.80
    k
    0.79
    kannya
    0.77
    é
    0.75
    ু
    0.73
    いた
    0.67
     OTA
    0.67
    kons
    0.66
    kiego
    0.65
    า
    0.62
    POSITIVE LOGITS
     tho
    0.62
    ized
    0.61
    .
    0.60
     если
    0.59
     ако
    0.58
    죠
    0.57
    2
    0.57
     اگه
    0.56
     हालाँकि
    0.56
     когато
    0.55
    Activations Density 0.104%

    No Known Activations