© 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. 67971
    Prev
    Next
    INDEX
    Explanations

    case, which is, white with, demons masquer

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

    oil, bacteria, couples

    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
    產
    0.48
    ąd
    0.47
    ítez
    0.46
    کر
    0.46
    rać
    0.46
    ół
    0.45
    捍
    0.45
    髗
    0.44
    KERNEL
    0.44
    atip
    0.44
    POSITIVE LOGITS
    s
    0.48
     aliexpress
    0.45
     anthrop
    0.45
     cigarette
    0.44
     meisten
    0.44
    banks
    0.44
     majority
    0.43
     cigarettes
    0.43
    mort
    0.42
     flawless
    0.42
    Activations Density 0.002%

    No Known Activations