© 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. 87079
    Prev
    Next
    INDEX
    Explanations

    Stephane

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

    This neuron flags occurrences of proper names or unique identifiers (e.g. personal names, place names, API/library names, or other named entities).

    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
    硖
    -2.89
    觏
    -2.70
    0
    -2.61
    嫱
    -2.53
    趼
    -2.47
    this
    -2.45
    蛩
    -2.45
    </strong>
    -2.44
     शुर
    -2.39
     این
    -2.36
    POSITIVE LOGITS
    籥
    2.72
    
    2.64
     are
    2.61
     infuse
    2.53
    僦
    2.48
    乀
    2.47
    
    2.45
    傒
    2.42
     ofere
    2.42
    熥
    2.38
    Activations Density 0.011%

    No Known Activations