© 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. 22-GEMMASCOPE-RES-131K
    7. 54360
    Prev
    Next
    INDEX
    Explanations

    describing states or examples

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find floating‐point numbers (numeric tokens containing a decimal point).

    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
    axy
    -1.11
    铝
    -1.01
    eek
    -1.00
    uch
    -0.99
     bla
    -0.98
    XXXX
    -0.98
     ith
    -0.98
     Foul
    -0.96
    iS
    -0.96
    oO
    -0.96
    POSITIVE LOGITS
    <bos>
    1.20
     steadily
    1.12
    Dá
    1.09
     wußte
    1.05
    的
    1.03
    に行ってきました
    1.02
     venuto
    1.01
    ですので
    1.00
     Händen
    0.98
     other
    0.97
    Activations Density 0.010%

    No Known Activations