© 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-16K
    7. 11289
    Prev
    Next
    INDEX
    Explanations

    according to

    np_acts-logits-general · gemini-2.5-flash-lite

    according to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0.64
     Westinghouse
    0.55
     WPF
    0.51
     CBIT
    0.51
    作为
    0.50
    ]}
    0.49
    ОР
    0.49
    СФ
    0.49
    ТС
    0.48
     rempl
    0.48
    POSITIVE LOGITS
     menurut
    0.83
     Menurut
    0.74
    According
    0.71
     Según
    0.71
    Menurut
    0.70
    estimates
    0.62
    theory
    0.62
    according
    0.61
     According
    0.60
    によると
    0.60
    Activations Density 0.078%

    No Known Activations