© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 261069
    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
    Negative Logits
     chiedere
    0.52
     chied
    0.51
    谊
    0.50
     美
    0.48
     изобре
    0.48
     passo
    0.47
     slay
    0.47
    <0xAB>
    0.46
     bắt
    0.46
     predmet
    0.45
    POSITIVE LOGITS
    ΝΑ
    0.52
    ántica
    0.52
    Salary
    0.47
    {(\
    0.47
    児
    0.47
    に伴
    0.46
    ﺢ
    0.44
    TAM
    0.43
    朋友們
    0.43
    ್ಟ
    0.43
    Activations Density 0.001%

    No Known Activations