© 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. 12892
    Prev
    Next
    INDEX
    Explanations

    apostrophes followed by contractions

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

    quoted words like country stats filename

    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
    of
    0.79
    ט
    0.77
     of
    0.74
    ।
    0.71
    2
    0.67
    ")
    0.65
    ?
    0.65
     for
    0.64
    3
    0.64
    ator
    0.64
    POSITIVE LOGITS
    deki
    0.57
     in
    0.56
    andez
    0.54
    O
    0.54
    U
    0.54
    இந்தப்
    0.53
    "{
    0.52
    ইন
    0.52
     phiên
    0.52
     இந்தப்
    0.52
    Activations Density 1.565%

    No Known Activations