© 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. 16-GEMMASCOPE-2-RES-16K
    7. 471
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    с
    0.59
    س
    0.49
    是
    0.46
    "
    0.44
    I
    0.44
    斯
    0.44
    다
    0.44
    ો
    0.41
    ని
    0.41
    し
    0.40
    POSITIVE LOGITS
    x
    0.68
    ad
    0.62
    is
    0.61
    ul
    0.52
    at
    0.52
    an
    0.51
    ق
    0.50
    cı
    0.49
    xv
    0.48
    xk
    0.48
    Activations Density 4.525%

    No Known Activations