© 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. 92267
    Prev
    Next
    INDEX
    Explanations

    connections over, why people, quick fixes

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

    describing or specifying states

    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
     Cisco
    0.48
     डिज
    0.47
     سلاٹ
    0.46
     દવા
    0.45
     excepto
    0.43
     Bernd
    0.43
    ربعة
    0.42
    ừ
    0.42
     ceded
    0.41
     Nursery
    0.41
    POSITIVE LOGITS
     valv
    0.52
     soulful
    0.45
     chord
    0.45
     harmonic
    0.44
     obstructive
    0.43
    olinium
    0.43
     discernment
    0.43
    价值观
    0.42
    MRP
    0.42
     downregulation
    0.42
    Activations Density 0.002%

    No Known Activations