© 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. 56733
    Prev
    Next
    INDEX
    Explanations

    regular basis

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

    pet products

    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
    ོ
    0.50
     kampus
    0.49
     completes
    0.48
     november
    0.47
     loc
    0.47
     nasceu
    0.47
    𝗈
    0.46
     hes
    0.46
    ës
    0.46
     lok
    0.46
    POSITIVE LOGITS
     radioactive
    0.49
     ನಡೆಯ
    0.44
     миллионов
    0.43
     زين
    0.43
     หนู
    0.43
     вре
    0.42
    rzez
    0.42
    嚢
    0.41
    dihydroxy
    0.41
    Trich
    0.41
    Activations Density 0.001%

    No Known Activations