© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92684
    Prev
    Next
    INDEX
    Explanations

    fees and dentistry

    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
     консульта
    0.42
    苌
    0.42
    GTUIKit
    0.42
    อยู่ใน
    0.41
     מצ
    0.40
     রাখিয়া
    0.40
    抟
    0.40
    சா
    0.40
    袄
    0.39
    夎
    0.39
    POSITIVE LOGITS
     birkaç
    0.45
     frugal
    0.45
     çeşitli
    0.43
     materiais
    0.43
     alguns
    0.42
     ferramentas
    0.42
     ahuv
    0.42
     outils
    0.41
     quelques
    0.41
     forse
    0.41
    Activations Density 0.006%

    No Known Activations