© 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. 205735
    Prev
    Next
    INDEX
    Explanations

    specific phrases and their usual continuations

    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
    Negative Logits
    市内
    0.38
    rijving
    0.37
     додат
    0.36
    বেদন
    0.36
     roce
    0.36
     brightening
    0.36
    เพิ่ม
    0.35
     connexion
    0.35
     requisition
    0.35
    잔
    0.35
    POSITIVE LOGITS
     మాత్రమే
    0.50
     seuls
    0.48
     fanáticos
    0.44
     willfully
    0.43
     மட்டுமே
    0.42
     unapolog
    0.42
     فقط
    0.41
    把自己
    0.41
    专注于
    0.41
     pilotos
    0.41
    Activations Density 0.015%

    No Known Activations