© 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. 13732
    Prev
    Next
    INDEX
    Explanations

    relevant

    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
    꼼
    0.66
    없이
    0.54
    աջ
    0.50
    বধূ
    0.50
     teşekkür
    0.50
     đãi
    0.49
    वरिश
    0.48
     Ahl
    0.48
    rum
    0.47
    摊
    0.47
    POSITIVE LOGITS
     relevant
    4.84
    relevant
    4.66
     Relevant
    4.59
    Relevant
    4.53
     relevante
    4.03
     relevantes
    3.84
     relev
    3.66
     pertinent
    3.56
     relevance
    3.50
     Relevance
    3.39
    Activations Density 0.124%

    No Known Activations