© 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. 253772
    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_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
    ும்பி
    0.57
     Сурикова
    0.55
     Zool
    0.53
    oscope
    0.52
     Realt
    0.51
     inilah
    0.50
    ’
    0.46
     Ebert
    0.45
     BMC
    0.45
     Podcasts
    0.45
    POSITIVE LOGITS
     。
    0.70
    。
    0.65
     በ
    0.63
    $.
    0.61
    問題
    0.61
    ۔
    0.61
    ।
    0.59
    ا
    0.57
    ።
    0.57
     إلى
    0.55
    Activations Density 0.050%

    No Known Activations