© 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. 22-GEMMASCOPE-RES-131K
    7. 92928
    Prev
    Next
    INDEX
    Explanations

    DNA synthesis, extraction, damage

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

    references to DNA in scientific or biological contexts.

    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_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
    荩
    -2.55
    乆
    -2.50
     δεν
    -2.30
    全都
    -2.22
     Then
    -2.22
    ll
    -2.14
    外部
    -2.14
    未完
    -2.11
    This
    -2.06
    　　*
    -2.06
    POSITIVE LOGITS
     were
    2.41
    ConfigureAwait
    1.98
     tetapi
    1.95
     וב
    1.95
    🐢
    1.89
    мии
    1.88
     Herausforderung
    1.80
     ups
    1.78
     In
    1.76
     Está
    1.76
    Activations Density 0.031%

    No Known Activations