© 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. 45653
    Prev
    Next
    INDEX
    Explanations

    trillion and billion values

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

    This neuron detects numeric tokens and number-like substrings (digits, numeric prefixes/suffixes, and units) 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
     Gob
    -0.84
     three
    -0.78
    降低
    -0.77
    setTitle
    -0.75
     Three
    -0.71
     institucional
    -0.71
     crow
    -0.70
     at
    -0.70
    Three
    -0.69
     received
    -0.68
    POSITIVE LOGITS
     trillion
    3.95
     tri
    3.31
    tri
    2.95
     Tri
    2.66
     billions
    2.53
     quadril
    2.44
    Tril
    2.39
    Tri
    2.34
     TRI
    2.05
     tril
    2.00
    Activations Density 0.079%

    No Known Activations