© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70185
    Prev
    Next
    INDEX
    Explanations

    hypocrisy and hypo- terms

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

    The neuron strongly activates on words and prefixes expressing “hypocrisy” or “hypocritical” in various forms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     akin
    -2.19
                
    -2.05
     Then
    -1.96
     likened
    -1.95
    л
    -1.94
     neuen
    -1.92
     ablaze
    -1.92
     applauded
    -1.91
     sogenannten
    -1.91
     ),
    -1.89
    POSITIVE LOGITS
    ↵
    2.11
    鷽
    2.11
    的声音
    2.00
    mittelt
    1.98
     своим
    1.98
    </b>
    1.94
     tne
    1.91
    }$
    1.88
    的力量
    1.88
    </
    1.86
    Activations Density 0.008%

    No Known Activations