© 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. 90702
    Prev
    Next
    INDEX
    Explanations

    persecution, harassment, targeting

    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
     riots
    -0.87
    Masukkan
    -0.84
     looting
    -0.84
    anatom
    -0.82
     пароль
    -0.82
     murders
    -0.81
     crimes
    -0.79
    மா
    -0.78
     debate
    -0.77
     discounts
    -0.77
    POSITIVE LOGITS
     persecution
    1.69
     vendetta
    1.52
     vindic
    1.52
     harassment
    1.50
     targeting
    1.48
     targeted
    1.40
     persec
    1.35
    targeting
    1.23
     persecu
    1.20
     Kafka
    1.20
    Activations Density 0.069%

    No Known Activations