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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10854
    Prev
    Next
    INDEX
    Explanations

    1. The / Project / Assessment / Choosing / Found / Understanding / Core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     minder
    0.99
    อย่า
    0.98
     treb
    0.97
     ace
    0.96
     vực
    0.95
     fielder
    0.93
    и
    0.93
     gan
    0.92
     обви
    0.92
     Nxf
    0.92
    POSITIVE LOGITS
    ﺐ
    1.13
    یت
    1.01
    ﻒ
    0.97
    ﺖ
    0.96
    es
    0.96
    ן
    0.90
    elijkheid
    0.89
    ză
    0.89
    isatie
    0.89
    ﻚ
    0.88
    Activations Density 0.271%

    No Known Activations