© 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. 49884
    Prev
    Next
    INDEX
    Explanations

    cartoon violence

    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
    databind
    -0.75
    fet
    -0.74
     Spiders
    -0.69
    イルド
    -0.69
    orme
    -0.69
    یفون
    -0.68
     Dubai
    -0.67
    Ί
    -0.67
     fort
    -0.67
    lieger
    -0.66
    POSITIVE LOGITS
     Warner
    1.18
     Bugs
    1.15
    Warner
    1.10
     cartoons
    1.10
     toon
    1.09
    Carto
    1.04
     Acme
    1.00
    cartoon
    0.99
     cartoon
    0.98
     Tasmanian
    0.98
    Activations Density 0.019%

    No Known Activations