© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117354
    Prev
    Next
    INDEX
    Explanations

    original [noun]

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

    This neuron selectively fires on the word “Original.”

    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
     início
    -0.88
    说到
    -0.87
     Gäste
    -0.85
    給我
    -0.83
    赑
    -0.82
     relatório
    -0.81
     parlare
    -0.79
     aficionados
    -0.79
    随便
    -0.79
    Bereits
    -0.79
    POSITIVE LOGITS
     original
    1.45
     Original
    1.39
    original
    1.34
    Original
    1.23
    getOriginal
    1.19
     thinkers
    1.13
     sin
    1.13
     ORIGINAL
    1.05
     ideas
    1.02
     artwork
    1.02
    Activations Density 0.017%

    No Known Activations