© 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. 45738
    Prev
    Next
    INDEX
    Explanations

    Rox Kop elast

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

    The neuron principally fires on capitalized named entities—people’s names, place names, organization names, team names, and acronyms.

    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
            
    -3.11
     When
    -3.02
    「
    -2.70
    this
    -2.67
     mendatang
    -2.50
    })}
    -2.50
    *
    -2.39
    "",
    -2.38
    ]
    -2.36
     []);
    -2.34
    POSITIVE LOGITS
    蹰
    2.94
    ዡ
    2.91
    两人的
    2.89
     帅气
    2.75
     rencont
    2.70
     partag
    2.70
    秾
    2.69
     glorified
    2.64
     velmi
    2.61
     hugely
    2.61
    Activations Density 0.028%

    No Known Activations