© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74936
    Prev
    Next
    INDEX
    Explanations

    advocating suicide, Wikipedia, shaping, freedom, Vitamin, Increased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    в
    0.44
     samot
    0.43
    سته
    0.43
     Colon
    0.41
    र्गन
    0.41
     recepción
    0.40
    слу
    0.40
    두
    0.40
    orgen
    0.39
    igay
    0.39
    POSITIVE LOGITS
     ditch
    0.43
     Sood
    0.42
     проекти
    0.42
     procès
    0.42
    ዒ
    0.41
     поли
    0.41
     تغییر
    0.41
     polymeric
    0.41
     жела
    0.41
     roadway
    0.41
    Activations Density 0.004%

    No Known Activations