© 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. 62998
    Prev
    Next
    INDEX
    Explanations

    references and code structure symbols

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

    The neuron activates on standalone numeric tokens (i.e. numbers).

    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
     cortina
    -1.00
     você
    -0.87
     antik
    -0.84
     Arquivado
    -0.83
     Anglican
    -0.82
     habis
    -0.82
     fhould
    -0.81
    رحلة
    -0.81
     tonel
    -0.80
    runOnUiThread
    -0.80
    POSITIVE LOGITS
    crivez
    0.93
    Vert
    0.92
    offers
    0.91
    abstractmethod
    0.91
    believe
    0.88
    particularly
    0.87
    aira
    0.86
     parámetros
    0.85
     perciò
    0.84
     프
    0.82
    Activations Density 0.002%

    No Known Activations