© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22811
    Prev
    Next
    INDEX
    Explanations

    prices, duration, or recipients

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

    This neuron activates on the word “for” when it’s being used to introduce a quantity or price (e.g. “for $33,” “for 145,” etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ?”
    -2.20
    “
    -1.80
    	
    -1.76
     .”
    -1.71
    ,”
    -1.66
     AppBundle
    -1.65
    !”
    -1.63
     was
    -1.63
    })$.
    -1.58
    ...”
    -1.56
    POSITIVE LOGITS
    Kepala
    1.55
    offerta
    1.49
     mangled
    1.41
    ーん
    1.40
     signifikan
    1.38
    しましたが
    1.34
     quella
    1.34
    ệu
    1.33
    الان
    1.32
     เป็น
    1.31
    Activations Density 0.021%

    No Known Activations