© 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. 81118
    Prev
    Next
    INDEX
    Explanations

    quantifying physical dimensions

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

    The neuron activates on numeric tokens, especially measurements or counts (e.g. runway lengths, plant dimensions, counts).

    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
     في
    -1.03
    marily
    -0.89
     baixo
    -0.88
     messo
    -0.85
     یکی
    -0.85
    diği
    -0.85
    graphers
    -0.84
    bietet
    -0.82
     week
    -0.82
    чини
    -0.82
    POSITIVE LOGITS
     approximately
    2.86
     approx
    2.30
     measuring
    2.20
     about
    2.14
    約
    2.08
    approximately
    1.94
     yaklaşık
    1.81
    约
    1.81
     roughly
    1.80
    Approximately
    1.80
    Activations Density 0.237%

    No Known Activations