© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32770
    Prev
    Next
    INDEX
    Explanations

    argument or Proposition

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

    The neuron activates on numeric tokens (sequences of digits), i.e. it detects 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_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
     obligatorio
    -0.71
    散
    -0.71
    lords
    -0.70
    贄
    -0.69
     publicação
    -0.69
     detective
    -0.68
     teman
    -0.68
    Market
    -0.67
    pum
    -0.67
    
    -0.66
    POSITIVE LOGITS
    Depression
    0.68
     RU
    0.66
     रुप
    0.65
    ignation
    0.64
     mig
    0.64
     progenitor
    0.64
     Diploma
    0.64
    iestety
    0.63
     Ha
    0.63
     reta
    0.61
    Activations Density 0.086%

    No Known Activations