© 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. 12905
    Prev
    Next
    INDEX
    Explanations

    python code

    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
     کاروبار
    0.52
     optimum
    0.49
     সুরক্ষিত
    0.49
    🤣
    0.48
    院
    0.48
     टॉपिक
    0.47
     جاری
    0.47
    炮
    0.47
    ixa
    0.47
     extract
    0.47
    POSITIVE LOGITS
    jim
    0.57
     Deps
    0.56
    ilim
    0.55
     Shots
    0.52
    शेष
    0.51
     क्यूब
    0.51
    ลิง
    0.49
    itim
    0.49
     JIM
    0.49
     коль
    0.48
    Activations Density 0.040%

    No Known Activations