© 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. 102468
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and differences

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

    The main thing this neuron does is pick out numeric quantities or measurements (digits, numerical values, and units).

    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
    especially
    -1.20
     and
    -1.12
    despite
    -1.08
    particularly
    -1.02
    ldon
    -1.02
     sereia
    -1.00
    resulting
    -1.00
    今晚
    -0.99
    accompanied
    -0.99
    neither
    -0.97
    POSITIVE LOGITS
     minus
    3.56
     multiplied
    2.73
    minus
    2.67
     plus
    2.33
    Minus
    2.20
     divided
    2.06
     Minus
    2.00
     плюс
    2.00
    MINUS
    1.83
     мину
    1.81
    Activations Density 0.150%

    No Known Activations