© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118899
    Prev
    Next
    INDEX
    Explanations

    gone viral

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

    content that has "gone viral" or is trending/spreading online.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     захворювання
    -0.74
    צוע
    -0.72
    STATIC
    -0.71
    cwd
    -0.71
     befolk
    -0.71
    DYNAMIC
    -0.71
    образие
    -0.70
    鈮
    -0.70
    heitsbild
    -0.69
    Kalau
    -0.68
    POSITIVE LOGITS
     viral
    5.97
    viral
    4.53
     Viral
    4.50
    Viral
    4.13
     vir
    2.94
     VIR
    2.72
     trending
    2.55
     virus
    2.25
    病毒
    2.23
    VIR
    2.09
    Activations Density 0.041%

    No Known Activations