© 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. 35695
    Prev
    Next
    INDEX
    Explanations

    positioning in specific locations

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

    The neuron activates on numeric tokens (e.g. integer or decimal values).

    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
     devraient
    -1.22
    trying
    -1.13
     '*':
    -1.09
    xiaomi
    -1.03
    ༈
    -1.01
     constater
    -1.00
     NKC
    -0.99
     fonctionnent
    -0.98
     appels
    -0.98
     lieux
    -0.97
    POSITIVE LOGITS
     the
    1.01
     sebuah
    0.99
     their
    0.99
     nestled
    0.95
     history
    0.94
     established
    0.94
     mankind
    0.94
    階の
    0.93
    İY
    0.91
     ......
    0.91
    Activations Density 0.106%

    No Known Activations