© 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. 10-GEMMASCOPE-RES-131K
    7. 65273
    Prev
    Next
    INDEX
    Explanations

    far more or less

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

    This neuron detects the comparative intensifier “more” (as in “more successful,” “more efficient,” “far more,” etc.).

    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
    锃
    -2.08
    尨
    -1.93
    转头
    -1.92
    荦
    -1.90
     parachoque
    -1.89
     helicópter
    -1.84
    ’)
    -1.83
    걔
    -1.83
    が多く
    -1.80
    壜
    -1.80
    POSITIVE LOGITS
    5
    2.34
    是
    2.33
    4
    2.33
    需要
    2.27
    7
    2.14
    3
    2.06
    第一
    2.06
    6
    2.05
    2
    2.03
    次
    1.94
    Activations Density 0.005%

    No Known Activations