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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73676
    Prev
    Next
    INDEX
    Explanations

    deoxy- compounds

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

    scientific terminology related to nucleosides, particularly chemical compounds containing 'deoxy' in their names.

    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
     Its
    -2.45
    .
    -2.34
     The
    -2.08
     eenige
    -1.90
    力が
    -1.85
    <bos>
    -1.80
     are
    -1.78
    凩
    -1.77
    CURLOPT
    -1.76
    
    -1.76
    POSITIVE LOGITS
    {
    2.77
    ・・・・・・・・
    2.13
    1
    2.11
    𐐪
    2.09
     Pemain
    2.08
    ISATION
    1.98
    2
    1.91
    嶇
    1.91
    жений
    1.90
    besos
    1.90
    Activations Density 0.026%

    No Known Activations