© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13147
    Prev
    Next
    INDEX
    Explanations

    balance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afield
    0.54
     হানাদার
    0.54
    陋
    0.49
    ვი
    0.49
     фраг
    0.48
    Suffix
    0.48
    Fragment
    0.46
     Consolidated
    0.45
     inmediato
    0.45
    )%>%
    0.44
    POSITIVE LOGITS
     balance
    4.28
    balance
    4.03
     balancing
    4.03
     балан
    4.03
     Balance
    3.98
     balances
    3.91
    Balance
    3.81
     BALANCE
    3.78
    平衡
    3.75
    バランス
    3.64
    Activations Density 0.180%

    No Known Activations