© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26628
    Prev
    Next
    INDEX
    Explanations

    persons and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    هرات
    0.38
    Resistance
    0.38
    🚺
    0.38
    ンの
    0.37
    ឥត
    0.37
    ยน
    0.37
    গতির
    0.37
     വനി
    0.37
    <_
    0.36
    бие
    0.35
    POSITIVE LOGITS
     sufferers
    1.16
     persons
    1.13
     Persons
    1.01
     osoby
    1.01
     personer
    1.00
    Persons
    1.00
     people
    0.96
     osób
    0.93
     pessoas
    0.92
     personnes
    0.92
    Activations Density 0.002%

    No Known Activations