© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93224
    Prev
    Next
    INDEX
    Explanations

    variety of, self-concept, proof

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

    The main thing this neuron does is find numeric tokens (especially years and other numbers) 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
    楔
    -0.87
     zespół
    -0.83
     your
    -0.83
     новые
    -0.83
    </h6>
    -0.82
     unserer
    -0.80
    =
    -0.79
    ：《
    -0.79
     Как
    -0.78
    AGB
    -0.77
    POSITIVE LOGITS
    <eos>
    0.93
     presented
    0.87
     Annotation
    0.86
     ""
    0.81
     aceasta
    0.79
    上がった
    0.78
    されており
    0.78
    strado
    0.78
     appended
    0.78
     this
    0.77
    Activations Density 0.232%

    No Known Activations