© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11515
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names

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

    The neuron fires strongly on personal names (especially as part of email/blog signatures or greetings).

    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
     veřej
    -1.25
     envía
    -1.20
     decenas
    -1.18
    ὴν
    -1.17
     cuáles
    -1.16
    días
    -1.14
    tikai
    -1.13
     cuánt
    -1.13
     nació
    -1.11
     apoya
    -1.09
    POSITIVE LOGITS
    from
    1.47
    Again
    1.38
    Should
    1.36
     ),
    
    1.31
    THERE
    1.30
        
    1.27
     proste
    1.24
    when
    1.19
    dienne
    1.19
     elegan
    1.18
    Activations Density 0.079%

    No Known Activations