© 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. 34-GEMMASCOPE-RES-131K
    7. 48370
    Prev
    Next
    INDEX
    Explanations

    Houston Dynamo

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

    The neuron strongly activates on proper‐name tokens—especially capitalized place names, people’s names, organizations, etc.—i.e. named‐entity words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    strophy
    -0.82
    ELINE
    -0.81
     Rotor
    -0.79
     Hungarian
    -0.78
    formin
    -0.78
     svin
    -0.77
    OKU
    -0.76
     lege
    -0.75
     Greene
    -0.75
    eline
    -0.74
    POSITIVE LOGITS
     Camden
    0.92
     Offered
    0.72
     bereits
    0.70
    重庆
    0.68
     तब
    0.68
    etzal
    0.67
     Janis
    0.67
     offered
    0.65
    また
    0.64
    mère
    0.64
    Activations Density 0.018%

    No Known Activations