© 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. 13225
    Prev
    Next
    INDEX
    Explanations

    say "lie"

    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
    प्रभाव
    0.53
    สมัย
    0.53
    icketts
    0.52
    涔
    0.49
    佇
    0.48
     CED
    0.48
    Excess
    0.47
    আধ
    0.47
     قیم
    0.47
     Excessive
    0.46
    POSITIVE LOGITS
     lied
    3.11
     lie
    2.94
     lies
    2.86
    謊
    2.80
     lying
    2.78
     거짓
    2.78
    谎
    2.77
     falsehood
    2.73
     liar
    2.61
     झूठ
    2.59
    Activations Density 0.106%

    No Known Activations