© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105458
    Prev
    Next
    INDEX
    Explanations

    connecting numbers with or

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

    the word "or" when it introduces an equivalent or alternative measurement, quantity, or percentage.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     with
    -1.69
    }^{+\
    -1.66
     as
    -1.63
     欣赏
    -1.55
     ragazzo
    -1.55
     ragazza
    -1.52
    nå
    -1.50
    mybatisplus
    -1.48
    andangan
    -1.48
    鉀
    -1.46
    POSITIVE LOGITS
     
    1.66
    儅
    1.65
     "
    1.62
    そういう
    1.59
    が無い
    1.52
    −/−
    1.52
    很好的
    1.47
    地味
    1.46
    の中から
    1.45
    ガチ
    1.45
    Activations Density 0.011%

    No Known Activations