© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86311
    Prev
    Next
    INDEX
    Explanations

    evaluating quality or reasons

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

    The neuron selectively activates on occurrences of the adjective “questionable.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Ensuring
    -2.77
    鉿
    -2.70
    不斷
    -2.66
    {
    -2.64
    擄
    -2.61
    雖
    -2.59
    鵙
    -2.58
    嘗
    -2.56
    わから
    -2.55
     linken
    -2.53
    POSITIVE LOGITS
    ↵
    3.39
    犇
    3.16
    0
    2.94
    vantaged
    2.94
    ஂ
    2.86
    ጮ
    2.84
    ist
    2.63
    汭
    2.59
    七月
    2.52
    
    2.52
    Activations Density 0.005%

    No Known Activations