© 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. 45621
    Prev
    Next
    INDEX
    Explanations

    revenge and retaliation

    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
    eros
    -0.88
    StringVar
    -0.85
    abinieri
    -0.81
    ruption
    -0.79
    });
    -0.77
    roscopy
    -0.76
    coltà
    -0.75
     выпуска
    -0.75
    ली
    -0.75
    zzling
    -0.74
    POSITIVE LOGITS
     revenge
    5.91
     vengeance
    4.19
     Revenge
    4.16
    revenge
    4.13
    Revenge
    3.91
     avenge
    3.55
     payback
    3.27
     retaliation
    3.17
     venganza
    3.13
     aven
    3.11
    Activations Density 0.068%

    No Known Activations