© 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. 3149
    Prev
    Next
    INDEX
    Explanations

    hard work and hard drives

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

    This neuron robustly activates on occurrences of the word “hard.”

    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
    тата
    -0.82
     Arsen
    -0.81
    ργ
    -0.78
    Обра
    -0.76
    Florence
    -0.74
    exists
    -0.73
    АР
    -0.73
    WOMAN
    -0.71
     Florence
    -0.71
    кипе
    -0.71
    POSITIVE LOGITS
     earned
    1.21
     work
    0.81
    disk
    0.80
    earned
    0.79
    僖
    0.78
     lavoro
    0.77
     disk
    0.77
     hatte
    0.77
    rood
    0.73
    留下
    0.73
    Activations Density 0.028%

    No Known Activations