© 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. 178573
    Prev
    Next
    INDEX
    Explanations

    detects words like "park" or "stores"

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

    sexual orientation, True, make, Blank, men, Ma, anchor, Null, Keeping

    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
     hãng
    0.53
    作品
    0.47
    办理
    0.46
    鳎
    0.45
     Maulana
    0.45
    లు
    0.44
    仅
    0.44
    หน้า
    0.43
    鸿
    0.43
    ﻬ
    0.42
    POSITIVE LOGITS
     exerting
    0.55
    DETECT
    0.51
     Thereby
    0.50
     regain
    0.49
     vasodil
    0.48
     detect
    0.48
    park
    0.48
     stimulated
    0.48
     detects
    0.47
     reinforces
    0.47
    Activations Density 0.000%

    No Known Activations