© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58348
    Prev
    Next
    INDEX
    Explanations

    polygraph and lies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     öz
    -0.81
     Neph
    -0.76
    OLE
    -0.74
     Ríos
    -0.74
     sunscreen
    -0.74
     minhas
    -0.73
    アクション
    -0.72
    юр
    -0.71
    ր
    -0.71
     rabies
    -0.70
    POSITIVE LOGITS
     poly
    2.73
     lie
    2.05
     Poly
    1.95
    poly
    1.94
    Poly
    1.78
    POLY
    1.63
     POLY
    1.61
     Lie
    1.55
    Lie
    1.38
     поли
    1.31
    Activations Density 0.021%

    No Known Activations