© 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-65K
    7. 48454
    Prev
    Next
    INDEX
    Explanations

    * real * time

    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_65k_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
     Seaside
    0.51
     Peoples
    0.50
     People
    0.50
    0
    0.48
     Elizabethan
    0.46
    ع
    0.46
     Oceans
    0.46
    ELIG
    0.45
    ﻋ
    0.45
    人の
    0.44
    POSITIVE LOGITS
    лой
    0.55
    centered
    0.46
    onej
    0.44
    ította
    0.44
    úan
    0.43
    ému
    0.43
    ikleri
    0.43
    центра
    0.43
     президента
    0.43
     уя
    0.42
    Activations Density 0.004%

    No Known Activations