© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43303
    Prev
    Next
    INDEX
    Explanations

    first names followed by specific next words

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

    This neuron activates on personal names (i.e. proper names of people).

    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
    潆
    -2.98
    
    -2.39
    
    -2.22
    䊐
    -2.22
    NSY
    -2.16
    ︓
    -2.06
    
    -2.06
    𓆟
    -2.05
    MVH
    -2.03
     burbujas
    -2.02
    POSITIVE LOGITS
    2
    3.69
    7
    3.36
    5
    3.34
    0
    3.06
    6
    2.92
    8
    2.77
    4
    2.55
    1
    2.25
    $
    2.14
    one
    2.13
    Activations Density 0.001%

    No Known Activations