© 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. 174452
    Prev
    Next
    INDEX
    Explanations

    certain patients, performed on, opponents provided

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

    when or when

    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
    Not in Any Lists

    No Comments

    Negative Logits
    –
    0.55
     in
    0.53
     &
    0.53
    [
    0.53
    --
    0.52
     rumours
    0.52
    在
    0.52
    по
    0.49
    ,\
    0.47
    Т
    0.47
    POSITIVE LOGITS
    baptism
    0.59
     বিশ্ববিদ্যালয়ের
    0.57
     comunit
    0.54
    studentid
    0.54
     communaut
    0.52
    হোক
    0.52
     اید
    0.51
     comunidad
    0.51
    ște
    0.51
     artériel
    0.50
    Activations Density 0.001%

    No Known Activations