© 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. 94216
    Prev
    Next
    INDEX
    Explanations

    Next PostNext

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

    Leo, abbreviations, Google, dehydration

    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
     defraud
    0.55
    il
    0.53
    轉
    0.50
    រ
    0.49
     bollywood
    0.49
    location
    0.46
    法國
    0.46
    volunteer
    0.46
    ﻙ
    0.45
     fireplaces
    0.45
    POSITIVE LOGITS
    arene
    0.48
     edging
    0.45
    ານ
    0.44
    痉
    0.43
     LG
    0.42
     reple
    0.42
    首页
    0.41
     steered
    0.40
    TabText
    0.39
     Either
    0.39
    Activations Density 0.002%

    No Known Activations