© 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. 48811
    Prev
    Next
    INDEX
    Explanations

    footballer who plays

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

    The neuron activates on sequences of digits used as legal case or report citation 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
     one
    -0.98
     it
    -0.95
     this
    -0.82
     тела
    -0.75
     Presenter
    -0.75
    ➟
    -0.74
    ]#
    -0.74
     wereld
    -0.73
    anskrit
    -0.72
    numbered
    -0.72
    POSITIVE LOGITS
     the
    0.89
     연구
    0.81
    ној
    0.81
     navigateur
    0.80
    Combining
    0.79
    sivas
    0.79
     celebratory
    0.78
     usuario
    0.77
     imposter
    0.77
     his
    0.76
    Activations Density 0.026%

    No Known Activations