© 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. 63521
    Prev
    Next
    INDEX
    Explanations

    new coping

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

    calculating with variables

    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
    upaten
    0.47
    们
    0.46
    盟
    0.45
    anggil
    0.45
     रफी
    0.44
    믈
    0.44
    opharm
    0.43
    อม
    0.42
    来
    0.41
    amy
    0.41
    POSITIVE LOGITS
     gigantic
    0.47
     proprio
    0.44
     wheelchair
    0.44
     vampire
    0.44
     bigger
    0.43
     Savior
    0.43
     folder
    0.43
     gás
    0.42
     çiz
    0.42
     Blackberry
    0.42
    Activations Density 0.000%

    No Known Activations