© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 803
    Prev
    Next
    INDEX
    Explanations

    lying to people or about things

    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_10/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
    J
    -3.89
    K
    -3.20
    Z
    -3.17
    U
    -3.11
    R
    -3.09
    W
    -3.08
    N
    -3.03
    H
    -2.94
     .
    -2.89
     whom
    -2.88
    POSITIVE LOGITS
    }
    2.58
    cherichia
    2.30
     valentín
    2.25
     treacherous
    2.25
    洐
    2.23
    etlen
    2.20
    coloriage
    2.20
     daban
    2.20
    鐿
    2.17
     \&
    2.16
    Activations Density 0.002%

    No Known Activations