© 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. 59169
    Prev
    Next
    INDEX
    Explanations

    printed material dimensions

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

    This neuron detects descriptions of physical format specifications—especially numerical dimensions and size/format labels (e.g. “A5-size format”).

    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
    edish
    -0.76
     darauf
    -0.72
    patra
    -0.71
    Autoritní
    -0.71
    XV
    -0.69
     ebenso
    -0.69
     list
    -0.68
     and
    -0.68
    filtered
    -0.68
    tamia
    -0.68
    POSITIVE LOGITS
     booklet
    1.82
     booklets
    1.49
     pages
    1.21
     pamphlet
    1.20
     unbound
    1.17
     pagination
    1.16
     Booklet
    1.16
     saddle
    1.13
     folded
    1.06
    pagination
    1.03
    Activations Density 0.038%

    No Known Activations