© 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. 34-GEMMASCOPE-RES-131K
    7. 50281
    Prev
    Next
    INDEX
    Explanations

    humiliation, insult, shame

    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
     noci
    -0.88
     scary
    -0.86
    đèn
    -0.85
     scared
    -0.85
     positivos
    -0.85
     alibi
    -0.84
     conforto
    -0.84
     sodio
    -0.84
    decrypt
    -0.83
    歟
    -0.83
    POSITIVE LOGITS
     humiliation
    3.47
     humiliated
    2.98
     humili
    2.95
     humiliating
    2.88
     уни
    2.05
     insult
    2.03
     Hum
    1.91
    hum
    1.91
     insults
    1.73
    Hum
    1.66
    Activations Density 0.028%

    No Known Activations