© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125055
    Prev
    Next
    INDEX
    Explanations

    fake deceit deception

    np_acts-logits-general · gemini-2.5-flash-lite

    fake or disguise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Là
    0.48
    酺
    0.48
     המס
    0.47
    ΑΣ
    0.46
    的空间
    0.46
    酥
    0.46
     commenters
    0.45
    Έ
    0.45
    콜
    0.45
     INVESTMENT
    0.44
    POSITIVE LOGITS
     deceit
    0.55
     deception
    0.48
    偽
    0.46
     paura
    0.45
     fake
    0.44
     でも
    0.44
     नकली
    0.44
     거짓
    0.44
     phony
    0.43
     disgu
    0.43
    Activations Density 0.002%

    No Known Activations