© 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. 229628
    Prev
    Next
    INDEX
    Explanations

    assurance, role, percent, chords, people said

    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
     functors
    0.47
    jär
    0.47
    t
    0.47
     releases
    0.46
    )
    0.44
     sentient
    0.43
     Swal
    0.43
     undoubt
    0.43
     connues
    0.42
     pipelines
    0.42
    POSITIVE LOGITS
    ênh
    0.49
    ﻤ
    0.45
    的人
    0.44
    的数据
    0.44
    オリ
    0.44
     prépar
    0.44
    င
    0.43
     প্রস্তুত
    0.43
     તૈયાર
    0.43
    マンション
    0.42
    Activations Density 0.000%

    No Known Activations