© 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. 3794
    Prev
    Next
    INDEX
    Explanations

    entity prefixes

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

    The neuron fires on capitalized proper names or unique named entities (e.g. people’s surnames, brand names, or specialized terms).

    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
     erreich
    -2.45
    
    -2.34
    徊
    -2.28
     tiefe
    -2.27
     itinéraires
    -2.25
     étages
    -2.22
    嘴巴
    -2.14
    zelfde
    -2.13
    
    -2.13
    InstrumentedTest
    -2.11
    POSITIVE LOGITS
    d
    2.53
    ?
    2.45
    ]
    2.39
     delicately
    2.39
    ဴ
    2.38
    when
    2.34
    The
    2.30
    ve
    2.27
     behövs
    2.25
     tatlı
    2.22
    Activations Density 0.129%

    No Known Activations