© 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. 10-GEMMASCOPE-RES-131K
    7. 42341
    Prev
    Next
    INDEX
    Explanations

    . )

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

    This neuron strongly responds to the sentence-final period in boilerplate metadata lines—e.g. after dates, grant numbers, version citations, or license headers.

    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
    糴
    -2.05
    𓆏
    -1.91
    
    -1.89
    ymax
    -1.88
    甞
    -1.85
     sê
    -1.77
    ⾝
    -1.77
    colore
    -1.77
    橚
    -1.75
    淠
    -1.74
    POSITIVE LOGITS
    b
    1.80
     största
    1.75
    f
    1.70
    k
    1.70
     in
    1.68
    可以
    1.61
    ↵↵
    1.58
    </tr>
    1.55
    甚至
    1.55
     Maybe
    1.53
    Activations Density 0.001%

    No Known Activations