© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47887
    Prev
    Next
    INDEX
    Explanations

    national/government institutions

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

    The neuron activates on numeric tokens—especially multi‐digit numbers like years or other numerical data.

    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
     reachable
    -0.82
    daylight
    -0.74
     précédentes
    -0.74
    Lyric
    -0.71
     cabeça
    -0.71
     Sequel
    -0.71
     encuentras
    -0.70
    graffiti
    -0.70
    さっそく
    -0.69
    ubakar
    -0.69
    POSITIVE LOGITS
    empty
    0.85
     Implementation
    0.77
    offee
    0.77
    Implementation
    0.77
     effet
    0.73
     {}));
    0.72
     ?></
    0.72
    Paris
    0.71
     Empty
    0.71
    tab
    0.71
    Activations Density 0.026%

    No Known Activations