© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83750
    Prev
    Next
    INDEX
    Explanations

    proof of concept or principle

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

    The neuron selectively activates on the word “concept,” in particular when it appears in “proof‐of‐concept” or similar study descriptions.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     kaksi
    -1.55
     Manag
    -1.46
     masker
    -1.40
     ingredi
    -1.38
     GREEK
    -1.37
     Brussel
    -1.36
     نهر
    -1.35
     Wardrobe
    -1.33
     キャンプ
    -1.33
     between
    -1.33
    POSITIVE LOGITS
    ].
    1.82
    </td>
    1.75
          
    1.61
     eredeti
    1.61
    ”.
    1.59
    ↵↵
    1.58
    </sup>
    1.48
    鲣
    1.45
     salido
    1.45
     ".
    1.44
    Activations Density 0.075%

    No Known Activations