© 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. 84296
    Prev
    Next
    INDEX
    Explanations

    body parts and sides

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

    The neuron is detecting numeric measurements and quantity indicators (numbers and related units or statistical 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
    詆
    -0.79
    siguiente
    -0.76
     Betreuung
    -0.76
     tươi
    -0.75
    ванию
    -0.72
    kaa
    -0.72
    past
    -0.72
     terceiro
    -0.71
      “
    -0.71
    hört
    -0.71
    POSITIVE LOGITS
     dominant
    2.89
    dominant
    2.52
     Dominant
    2.16
     dominate
    2.14
    Domin
    2.09
     dominante
    1.88
     non
    1.72
     dominance
    1.63
     dominating
    1.59
     dominates
    1.59
    Activations Density 0.078%

    No Known Activations