© 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. 256828
    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
    じた
    0.47
    тических
    0.46
     związku
    0.43
     분포
    0.43
    啣
    0.43
    щення
    0.42
    િતિ
    0.42
     discernment
    0.41
    ме
    0.41
    জ্ঞ
    0.40
    POSITIVE LOGITS
     shakes
    0.49
    板
    0.46
     الماء
    0.45
     Alger
    0.45
    pan
    0.45
     ？
    0.44
    kaf
    0.44
    callow
    0.44
    pupp
    0.44
    te
    0.43
    Activations Density 0.001%

    No Known Activations