© 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. 254879
    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
     चैल
    0.51
    镙
    0.51
     Фурга
    0.49
    mLogin
    0.49
    ক্ষেত্র
    0.48
     لاہور
    0.48
     Maugin
    0.47
    鬯
    0.47
     म्हण
    0.47
     پایین
    0.46
    POSITIVE LOGITS
     impressive
    0.48
     wind
    0.46
     appreciated
    0.45
     stirs
    0.45
     impresses
    0.45
     conveys
    0.44
     fee
    0.43
     convey
    0.43
     Jerome
    0.42
    fee
    0.42
    Activations Density 0.000%

    No Known Activations