© 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. 10-GEMMASCOPE-RES-131K
    7. 39806
    Prev
    Next
    INDEX
    Explanations

    legal case identifiers

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

    This neuron responds to standalone numeric tokens (especially numbers with decimals).

    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
     „
    -1.62
     poignant
    -1.59
    AfterViewInit
    -1.59
     veritable
    -1.59
     fungerar
    -1.57
    在那里
    -1.52
    自己是
    -1.51
    ())){
    -1.46
    。”
    -1.43
     hittar
    -1.41
    POSITIVE LOGITS
    และ
    1.86
     și
    1.73
    A
    1.72
     generalmente
    1.70
     relativamente
    1.66
     AND
    1.62
     be
    1.58
      
    1.57
    живание
    1.56
    ︐
    1.53
    Activations Density 0.194%

    No Known Activations