© 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. 83145
    Prev
    Next
    INDEX
    Explanations

    cost effectiveness or percentages

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

    This neuron flags numeric percentage figures (e.g. “65 %”) indicating equity or ownership stakes.

    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
     crocs
    -0.82
    liston
    -0.78
     tecnológica
    -0.77
    である
    -0.75
     cystic
    -0.75
    suri
    -0.74
     chamado
    -0.73
     якого
    -0.73
    aktor
    -0.73
    Bonus
    -0.73
    POSITIVE LOGITS
     holds
    0.88
     iga
    0.82
    owning
    0.78
    ранда
    0.77
     inocente
    0.77
    ↓↓
    0.76
    ولت
    0.74
     acquired
    0.73
     peque
    0.73
    vital
    0.73
    Activations Density 0.014%

    No Known Activations