© 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. 149908
    Prev
    Next
    INDEX
    Explanations

    Christian Science

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

    fingers followed by parenthesis

    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
     an
    0.43
    la
    0.43
     owner
    0.42
     Youngstown
    0.41
    2
    0.41
    swear
    0.41
     प्लानिंग
    0.40
    ka
    0.40
     escalated
    0.39
     proprietors
    0.39
    POSITIVE LOGITS
    掝
    0.53
    ’’’’
    0.52
     ක්
    0.51
     челове
    0.50
     인간
    0.50
     trauer
    0.50
    られて
    0.50
     spécifiques
    0.49
     மனித
    0.49
    玛
    0.49
    Activations Density 0.000%

    No Known Activations