© 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. 60415
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation and contractions

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

    The neuron activates on numeric tokens, detecting numbers and digits 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
    军的
    -0.98
    
    -0.97
     aforementioned
    -0.95
    <u>
    -0.93
    ################
    -0.91
    IMAS
    -0.88
     Wikipedia
    -0.88
     Duits
    -0.88
    AppComponent
    -0.88
     weiterer
    -0.88
    POSITIVE LOGITS
    Here
    1.45
    <eos>
    1.36
    はこちらから
    1.25
     read
    1.23
     here
    1.18
     découvrez
    1.15
    这里
    1.13
     learn
    1.08
    在这里
    1.08
     pourra
    1.04
    Activations Density 0.159%

    No Known Activations