© 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. 49948
    Prev
    Next
    INDEX
    Explanations

    requests and inquiries

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

    The neuron activates primarily on the word “family” (and close variants) when it appears in the text.

    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
     müssen
    -0.92
     estacionamento
    -0.90
     moeten
    -0.89
     acabó
    -0.87
     perasaan
    -0.85
    idated
    -0.84
     relativistic
    -0.83
     révélé
    -0.82
    дожник
    -0.81
     équipe
    -0.80
    POSITIVE LOGITS
     request
    1.52
     requests
    1.42
     suggests
    1.38
     asks
    1.34
     ask
    1.34
     suggest
    1.32
    request
    1.31
    requests
    1.14
     prefer
    1.11
     requested
    1.11
    Activations Density 0.010%

    No Known Activations