© 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. 63032
    Prev
    Next
    INDEX
    Explanations

    Father's Day and work plan

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

    resorting to, irrational beliefs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     protesting
    0.45
     ppl
    0.42
     Ừ
    0.42
     Arrang
    0.41
     cricketers
    0.41
     croche
    0.41
    lubridate
    0.40
     khen
    0.40
     campaigners
    0.40
     repayments
    0.40
    POSITIVE LOGITS
    iduciary
    0.45
    п
    0.45
     Poisson
    0.44
     zunehm
    0.42
    起点
    0.42
    ckiego
    0.41
     интеллек
    0.41
    .'"
    0.40
     шли
    0.40
    ीट
    0.40
    Activations Density 0.000%

    No Known Activations