© 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. 78820
    Prev
    Next
    INDEX
    Explanations

    Nigerian elections

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

    The main thing this neuron does is detect numeric tokens (numbers and digit sequences).

    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
     imp
    -0.81
     medži
    -0.74
     pertinent
    -0.72
     ale
    -0.71
     identified
    -0.70
     encompassing
    -0.69
     />
    -0.68
    太好了
    -0.68
     Barr
    -0.68
     constituted
    -0.68
    POSITIVE LOGITS
     Nigerian
    0.98
     Nigeria
    0.93
    Nigerian
    0.90
     хими
    0.89
     niger
    0.84
    worfen
    0.84
    Nigeria
    0.83
     provincie
    0.82
    ACA
    0.82
    ☦
    0.82
    Activations Density 0.004%

    No Known Activations