© 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. 254513
    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
     magnific
    0.48
    伝える
    0.47
     Überg
    0.45
    儕
    0.43
     condemns
    0.42
    ћин
    0.42
     ప్రో
    0.42
     जिसके
    0.41
     価格
    0.41
    谴
    0.41
    POSITIVE LOGITS
     summaries
    0.49
     ont
    0.49
    iting
    0.48
    Any
    0.48
     aime
    0.48
    WAS
    0.48
    American
    0.47
    AD
    0.47
    UT
    0.47
     hospitals
    0.47
    Activations Density 0.000%

    No Known Activations