© 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. 71109
    Prev
    Next
    INDEX
    Explanations

    certain, oiled, similar, varied, forgiven

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

    financial or sensitive information

    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
     其
    0.45
     oth
    0.45
     prices
    0.45
     भने
    0.44
     say
    0.43
    ophenone
    0.43
     त्यो
    0.42
    น
    0.42
    p
    0.42
     says
    0.41
    POSITIVE LOGITS
     Probation
    0.52
     initiator
    0.50
    sprach
    0.45
    ʑ
    0.45
     কলেজে
    0.45
     assessor
    0.44
     ஆண்டுகளுக்கு
    0.44
    ﻪ
    0.44
    第一个
    0.43
     stipend
    0.43
    Activations Density 0.002%

    No Known Activations