© 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. 22-GEMMASCOPE-RES-131K
    7. 26251
    Prev
    Next
    INDEX
    Explanations

    places and countries

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

    The neuron activates strongly on tokens containing numbers (years, measurements, statistics, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     currently
    -0.90
    Begriffsklä
    -0.89
    ఉ
    -0.87
    “……”
    -0.86
     like
    -0.86
    مك
    -0.84
    carros
    -0.84
    collier
    -0.84
     recently
    -0.83
     usuário
    -0.83
    POSITIVE LOGITS
    icach
    0.95
    region
    0.94
    chandising
    0.79
     gradualmente
    0.75
     Flughafen
    0.73
    Poison
    0.73
     لهذه
    0.73
     этих
    0.73
     magnum
    0.73
    banco
    0.73
    Activations Density 0.024%

    No Known Activations