© 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. 75546
    Prev
    Next
    INDEX
    Explanations

    own description

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

    profanity and marketing terms

    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
    1
    0.53
    ₁
    0.53
    ge
    0.52
    da
    0.52
    0
    0.51
    nde
    0.49
    ma
    0.48
    ne
    0.47
    umi
    0.46
    di
    0.46
    POSITIVE LOGITS
    顧客
    0.45
    ন্ত
    0.43
    চৈত
    0.43
    ਰ
    0.42
    Thay
    0.42
     Loeb
    0.41
    лед
    0.41
     festive
    0.41
     Marlene
    0.41
    崚
    0.41
    Activations Density 0.001%

    No Known Activations