© 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. 36140
    Prev
    Next
    INDEX
    Explanations

    another or more of another

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

    The neuron fires on numerical tokens (digits and measurements, including integers and decimals).

    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
    為に
    -1.22
    になるので
    -1.20
     Bretaña
    -1.17
     siano
    -1.13
     każ
    -1.13
     този
    -1.09
     ite
    -1.09
    尤其是
    -1.09
     kilka
    -1.06
    たびに
    -1.04
    POSITIVE LOGITS
     another
    2.81
     more
    1.94
     other
    1.66
     again
    1.58
     a
    1.55
     أخرى
    1.54
     our
    1.52
    อีก
    1.49
     additional
    1.49
     one
    1.48
    Activations Density 0.019%

    No Known Activations