© 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. 259079
    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
     Де
    0.62
     테
    0.61
     הק
    0.58
     کر
    0.57
     데
    0.56
     탄
    0.53
     שע
    0.53
    𝗗
    0.52
    Я
    0.52
     เซ
    0.51
    POSITIVE LOGITS
     dále
    0.46
    努力
    0.44
     in
    0.43
     décidé
    0.42
    йдёт
    0.40
     savoir
    0.40
    出
    0.40
     décider
    0.39
    決
    0.39
    了下来
    0.38
    Activations Density 0.001%

    No Known Activations