© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5600
    Prev
    Next
    INDEX
    Explanations

    deception and lies

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

    misrepresentation, falsehood, deception

    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_53_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
    맡
    0.38
    രം
    0.37
    揮
    0.36
    quinazoline
    0.36
     متجه
    0.36
    锢
    0.36
     FETCH
    0.36
    umine
    0.35
    傍
    0.35
    갇
    0.34
    POSITIVE LOGITS
     거짓
    2.80
    谎
    2.64
     झूठ
    2.63
     deception
    2.58
    謊
    2.55
     deceit
    2.52
     lied
    2.50
     falsehood
    2.42
     deceptive
    2.41
     deceiving
    2.41
    Activations Density 0.218%

    No Known Activations