© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93422
    Prev
    Next
    INDEX
    Explanations

    software extensions

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

    The neuron consistently lights up on the token “extension” (in any casing or code‐related context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    栊
    -2.73
    鷽
    -2.70
    of
    -2.56
    '
    -2.56
     یا
    -2.50
     estadounid
    -2.48
     باسلام
    -2.45
     女性
    -2.45
     solu
    -2.44
    埽
    -2.42
    POSITIVE LOGITS
    趼
    2.69
    戬
    2.53
     insgesamt
    2.33
     gearing
    2.31
    紧接着
    2.27
    ↵
    2.27
     ярко
    2.22
     permitiendo
    2.22
     obecnie
    2.22
    時期
    2.22
    Activations Density 0.007%

    No Known Activations