© 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. 56572
    Prev
    Next
    INDEX
    Explanations

    unisex, hypoallergenic, efficacy

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

    Loaded from shape

    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
    这些人
    0.43
    奋
    0.43
    Ange
    0.40
    hur
    0.40
    tte
    0.40
    в
    0.39
    رض
    0.39
    Contributing
    0.39
    مر
    0.38
    tom
    0.38
    POSITIVE LOGITS
     celulares
    0.46
     primo
    0.45
     unisex
    0.45
     propietarios
    0.45
     janela
    0.44
     dado
    0.44
     hypoallergenic
    0.43
    ᱔
    0.43
     Unisex
    0.42
     eficacia
    0.42
    Activations Density 0.000%

    No Known Activations