© 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. 10-GEMMASCOPE-RES-131K
    7. 123653
    Prev
    Next
    INDEX
    Explanations

    genetic code sequences or natural language

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

    DNA/genetic sequences with nucleotide bases (like GC, TG, CT, AG).

    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_10/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
     That
    -2.56
    嵎
    -2.55
     signifikan
    -2.31
    ⸝
    -2.20
    輒
    -2.17
     How
    -2.14
    FieldOffset
    -2.13
    When
    -2.11
    檄
    -2.08
    PopMatrix
    -2.06
    POSITIVE LOGITS
     \
    3.23
    \
    2.42
    ↵
    2.42
     ‚
    2.36
    鬟
    2.27
    亖
    2.25
     بیشتر
    2.16
    
    2.06
     \"
    2.02
    ＇
    1.99
    Activations Density 0.007%

    No Known Activations