© 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. 81648
    Prev
    Next
    INDEX
    Explanations

    comic strips and cartoons

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of comic‐strip titles, characters, and related terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Articles
    -0.82
    猎
    -0.74
    playback
    -0.74
    ַּ
    -0.73
    诗
    -0.71
     filial
    -0.71
    ɵɵelementStart
    -0.69
    <thead>
    -0.66
     practicable
    -0.66
     Volunteers
    -0.66
    POSITIVE LOGITS
     comics
    2.14
     comic
    2.03
    comics
    1.66
     strip
    1.63
    comic
    1.62
     strips
    1.61
    Comics
    1.48
     cartoon
    1.41
     Comics
    1.39
    strips
    1.30
    Activations Density 0.039%

    No Known Activations