© 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. 49468
    Prev
    Next
    INDEX
    Explanations

    assignments and code constructs

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

    The neuron is triggered by numeric constants (i.e. literal numbers) in the code.

    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
     herinner
    -1.02
     trouw
    -1.01
     antwoord
    -0.98
    secuencias
    -0.94
    ridescent
    -0.93
     dzisiaj
    -0.93
     condenado
    -0.91
    unno
    -0.90
    onday
    -0.90
    pherds
    -0.89
    POSITIVE LOGITS
     (
    1.16
     colar
    1.03
     fantasia
    0.96
     cento
    0.96
     anormal
    0.93
     -(
    0.93
    -(
    0.93
     bucal
    0.92
     multa
    0.91
     (-
    0.89
    Activations Density 0.024%

    No Known Activations