© 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. 13522
    Prev
    Next
    INDEX
    Explanations

    technical domain language

    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
     sr
    0.58
     හ
    0.55
     er
    0.53
     recogn
    0.53
    识别
    0.49
     toutefois
    0.49
     recognising
    0.49
    씰
    0.49
     nk
    0.48
     हस्तक्षेप
    0.48
    POSITIVE LOGITS
    qquad
    0.64
    Avl
    0.62
    菡
    0.58
    ätt
    0.55
    Benzoimidazol
    0.54
    ත්‍
    0.53
     જિલ્
    0.53
                                  
    0.52
    وجد
    0.52
                                 
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.