© 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. 13413
    Prev
    Next
    INDEX
    Explanations

    process or condition

    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
     보세요
    0.94
    에요
    0.85
    게요
    0.82
    니까
    0.80
    예요
    0.80
     볼게요
    0.76
    어요
    0.75
     좋아요
    0.73
    이에요
    0.72
    었어요
    0.71
    POSITIVE LOGITS
    하며
    1.18
    하게
    1.15
    하였다
    1.15
    한다
    1.13
    했으며
    1.09
    함으로써
    1.04
    하거나
    1.03
    했고
    1.00
    하도록
    1.00
    하는데
    0.96
    Activations Density 0.004%

    No Known Activations