© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111475
    Prev
    Next
    INDEX
    Explanations

    cond or condition

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

    the word "cond" (or abbreviations/variables containing "cond") in technical or medical contexts.

    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
    觏
    -2.64
     semelh
    -2.59
    蟥
    -2.56
    푣
    -2.48
    ﻡ
    -2.47
     допомогою
    -2.47
    geſ
    -2.44
    薆
    -2.44
     have
    -2.42
    遑
    -2.42
    POSITIVE LOGITS
    ↵
    3.86
    \
    3.77
    </sup>
    3.09
    E
    2.69
    </em>
    2.48
    敉
    2.45
    他们是
    2.44
     )
    2.44
    初の
    2.38
    2
    2.36
    Activations Density 0.004%

    No Known Activations