© 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. 98962
    Prev
    Next
    INDEX
    Explanations

    Registry, testing, Q

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

    The neuron fires on mentions of “Registry” (e.g. code or documentation references to registries).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    罍
    -1.85
    鹪
    -1.77
     poto
    -1.60
    菒
    -1.59
    錸
    -1.59
    垆
    -1.56
     tâ
    -1.54
    
    -1.53
    螣
    -1.52
    筇
    -1.52
    POSITIVE LOGITS
    ’
    2.17
    ]
    1.73
    从此
    1.53
    9
    1.48
    varlak
    1.46
    がこの
    1.45
     新聞
    1.45
    欵
    1.45
    ].
    1.41
    品の
    1.39
    Activations Density 0.000%

    No Known Activations