© 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. 84166
    Prev
    Next
    INDEX
    Explanations

    comics and medical terms

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

    comic book and publication references including titles, issue numbers, and dates.

    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
     adaptation
    -0.86
     adapted
    -0.81
     ISA
    -0.76
    Adj
    -0.76
    divine
    -0.75
    adaptation
    -0.74
     PAT
    -0.73
     Shaft
    -0.73
    头部
    -0.73
    adak
    -0.73
    POSITIVE LOGITS
    owią
    0.85
    umentos
    0.84
     estimé
    0.81
    ᄉ
    0.81
     telah
    0.79
    showMessage
    0.76
    checkpoint
    0.75
    ㅊ
    0.75
    ᵃ
    0.75
    销售
    0.73
    Activations Density 0.018%

    No Known Activations