© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124609
    Prev
    Next
    INDEX
    Explanations

    You are here

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

    The neuron fires on numeric tokens—especially numbers (often with decimal points) in tabular or data‐table contexts.

    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
    8
    -1.73
     of
    -1.59
    jangkau
    -1.51
    Hlav
    -1.48
      -
    -1.46
    從
    -1.44
    your
    -1.44
     aptly
    -1.43
     calefacción
    -1.41
    Моя
    -1.38
    POSITIVE LOGITS
    </td>
    1.98
     nyní
    1.66
    了很多
    1.59
     потому
    1.55
     اگر
    1.55
      
    1.55
     Relaciones
    1.53
     svou
    1.52
    戗
    1.45
    </h5>
    1.45
    Activations Density 0.004%

    No Known Activations