© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14693
    Prev
    Next
    INDEX
    Explanations

    confusion

    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
    祷
    0.59
     prist
    0.53
     Harsh
    0.52
     극한
    0.51
    삭
    0.50
    ICIENCY
    0.49
    クタ
    0.49
    瑕
    0.49
    禱
    0.49
    豪
    0.48
    POSITIVE LOGITS
     confusion
    4.59
     confuse
    4.41
    confusion
    4.34
     confused
    4.31
     Confusion
    4.31
    Confusion
    4.22
     confusing
    4.16
     confuses
    4.13
     confusión
    4.00
     confus
    3.89
    Activations Density 0.178%

    No Known Activations