© 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. 10-GEMMASCOPE-RES-131K
    7. 39428
    Prev
    Next
    INDEX
    Explanations

    balance between opposing elements

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

    The neuron primarily activates on numeric tokens (multi‐digit 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_10/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
    鬭
    -3.39
     gestartet
    -2.95
    怱
    -2.92
    栳
    -2.92
    ことを
    -2.83
     alcune
    -2.81
    盌
    -2.78
     Jeden
    -2.55
     :"
    -2.52
     Whilst
    -2.50
    POSITIVE LOGITS
     strengthen
    3.20
    Ⲉ
    2.94
    e
    2.83
    U
    2.81
     encourage
    2.80
     establish
    2.78
    J
    2.55
     immerse
    2.53
    Z
    2.53
     includes
    2.52
    Activations Density 0.008%

    No Known Activations