© 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. 94069
    Prev
    Next
    INDEX
    Explanations

    type, price, token, subdivision

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

    The neuron fires on the definite article “the.”

    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
     divertir
    -1.07
    Helmut
    -1.00
    OTROS
    -1.00
    erver
    -0.99
    んご
    -0.98
    תם
    -0.95
    μαι
    -0.94
     населення
    -0.94
    Jörg
    -0.94
    Жит
    -0.93
    POSITIVE LOGITS
     type
    1.09
     certificate
    1.03
    }(
    1.03
    .
    1.02
     item
    0.97
     certification
    0.96
    <u>
    0.94
    O
    0.93
    _
    0.93
     Certification
    0.91
    Activations Density 0.000%

    No Known Activations