© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68347
    Prev
    Next
    INDEX
    Explanations

    historical atrocities and controversial statements

    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_22/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
     case
    -0.91
    ječ
    -0.91
    ijnlijk
    -0.89
    奮
    -0.87
     лечения
    -0.86
     alfabe
    -0.86
    руется
    -0.85
    🐻
    -0.82
    ристання
    -0.82
     おしゃれ
    -0.82
    POSITIVE LOGITS
    åt
    0.98
    wapV
    0.96
    脓
    0.95
     клави
    0.94
     chrétienne
    0.93
     decadent
    0.90
     かけ
    0.88
    誣
    0.88
    デューサー
    0.88
    hetamine
    0.87
    Activations Density 0.024%

    No Known Activations