© 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. 15818
    Prev
    Next
    INDEX
    Explanations

    AI assistant responses

    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
    那
    0.55
    astica
    0.55
    자와
    0.52
    جلد
    0.50
    olla
    0.50
    щиков
    0.50
     那
    0.49
    ələ
    0.49
    UIControlState
    0.48
    那种
    0.47
    POSITIVE LOGITS
    삽
    0.58
     lucru
    0.57
    ROY
    0.56
    accompan
    0.55
     میک
    0.55
     phép
    0.54
     प्रारूप
    0.54
     Chapman
    0.54
     stallion
    0.53
     tuberc
    0.53
    Activations Density 0.060%

    No Known Activations