© 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. 246851
    Prev
    Next
    INDEX
    Explanations

    medical terms and specific events

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     introspection
    0.47
     beast
    0.47
     Developed
    0.46
    =?,
    0.46
    ので
    0.46
    電子
    0.46
     (),
    0.46
    ]
    0.45
    (^
    0.45
     Pronghorn
    0.45
    POSITIVE LOGITS
    Signed
    0.54
    cheidung
    0.51
     விழு
    0.50
    alers
    0.50
    antoin
    0.50
    iar
    0.49
    èm
    0.48
    щать
    0.48
    чами
    0.47
    cadilly
    0.47
    Activations Density 0.000%

    No Known Activations