© 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. 13475
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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
     /></
    0.55
    лай
    0.52
     لوب
    0.52
     Bid
    0.52
    →</
    0.52
     జి
    0.52
    쥐
    0.50
     لوبی
    0.50
    itimes
    0.49
     ஈ
    0.49
    POSITIVE LOGITS
    ilerin
    0.55
    designs
    0.53
    петров
    0.53
    ведена
    0.52
    塔
    0.52
     coerc
    0.50
    provision
    0.49
     bakan
    0.49
     dena
    0.49
    珏
    0.49
    Activations Density 0.000%

    No Known Activations