© 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. 34-GEMMASCOPE-RES-131K
    7. 32588
    Prev
    Next
    INDEX
    Explanations

    the prior art

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

    This neuron detects 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
     POETRY
    -0.79
    ksan
    -0.78
    ''''
    -0.75
    coarse
    -0.73
     kleiner
    -0.72
    %^
    -0.71
    Bum
    -0.71
    maxi
    -0.70
     capacitación
    -0.70
     وت
    -0.70
    POSITIVE LOGITS
     underlined
    0.85
    ҫ
    0.83
     Roach
    0.82
    讓
    0.82
    نك
    0.79
     sentence
    0.79
    Από
    0.79
     potře
    0.78
    sentence
    0.77
    原神
    0.76
    Activations Density 0.004%

    No Known Activations