© 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. 103231
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and procedures

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

    The neuron is tuned to spotting numeric tokens and quantities (e.g. counts, years, measurements) in the text.

    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
    
    -0.80
    +|
    -0.77
    жина
    -0.76
    reachable
    -0.73
     Thorpe
    -0.73
     planos
    -0.73
     "¡
    -0.72
    enthe
    -0.71
     intervening
    -0.71
     avantages
    -0.71
    POSITIVE LOGITS
    Vla
    0.75
    Disciplina
    0.73
    rophoresis
    0.71
     disciplines
    0.71
     discipline
    0.71
    ڄ
    0.70
     approximation
    0.70
     orientation
    0.69
    úsica
    0.67
     گوید
    0.67
    Activations Density 0.036%

    No Known Activations