© 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. 252924
    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
     auxiliar
    0.50
    掻
    0.49
    덟
    0.48
     afore
    0.47
     auxiliary
    0.46
     inhomogeneities
    0.46
    olaire
    0.46
     phụ
    0.46
     âg
    0.46
     adı
    0.46
    POSITIVE LOGITS
    యత్
    0.49
    той
    0.48
    坌
    0.45
    Definitions
    0.45
    安定
    0.45
    出一
    0.45
     ক্যাথ
    0.43
    д
    0.43
    х
    0.43
    アンド
    0.42
    Activations Density 0.002%

    No Known Activations