© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71560
    Prev
    Next
    INDEX
    Explanations

    scientific notation and scale numbers

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

    The neuron activates on numeric tokens and numeric expressions (e.g. standalone digits, decimals, and numbers with unit-like context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    మీ
    -1.09
    Mbps
    -1.00
    一直
    -0.98
    guía
    -0.97
    taler
    -0.95
    cette
    -0.94
     Terkait
    -0.94
     sempre
    -0.93
     Apalagi
    -0.93
    ᱧ
    -0.93
    POSITIVE LOGITS
     rencont
    1.16
     appréci
    1.13
    くちゃ
    1.08
     billion
    1.05
     trillion
    1.03
     trouvent
    1.02
    άνι
    1.02
    Probl
    1.02
     soulign
    1.02
     unimaginable
    1.01
    Activations Density 0.059%

    No Known Activations