© 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. 13231
    Prev
    Next
    INDEX
    Explanations

    fake

    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
     ബു
    0.52
    ளாவ
    0.52
    たす
    0.50
    睏
    0.49
    شرين
    0.49
    ាស
    0.49
     जवाहर
    0.48
     multidiscipl
    0.48
     الخلا
    0.47
     느
    0.47
    POSITIVE LOGITS
     fake
    4.03
    fake
    3.81
     Fake
    3.72
    Fake
    3.69
    FAKE
    3.28
     counterfeit
    3.09
     नकली
    3.06
     phony
    3.00
    偽
    2.98
    假
    2.77
    Activations Density 0.143%

    No Known Activations