© 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. 152863
    Prev
    Next
    INDEX
    Explanations

    employment, payment, status

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

    contrast or concession constructions

    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
    葉
    0.52
     都
    0.49
    鈮
    0.45
     儿
    0.45
     以下
    0.45
    両
    0.44
    ರಲ್ಲಿ
    0.43
    ニュ
    0.43
    蘇
    0.43
    に関して
    0.42
    POSITIVE LOGITS
     ciudad
    0.47
    ;
    0.47
    oczes
    0.47
    ivas
    0.46
     città
    0.46
    ue
    0.46
    ﻒ
    0.44
     steamed
    0.44
     rainbows
    0.44
    iven
    0.43
    Activations Density 0.001%

    No Known Activations