© 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. 103509
    Prev
    Next
    INDEX
    Explanations

    commanded admiration or views

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

    The neuron activates on occurrences of the root “command” (in forms like command, commanded, commanding).

    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
     anstatt
    -2.11
    borderSide
    -2.09
    豳
    -2.06
    ﮨ
    -2.05
    鹇
    -2.03
    埛
    -2.02
    ￬
    -2.00
    ſelf
    -1.95
    linawan
    -1.91
    ばい
    -1.90
    POSITIVE LOGITS
    </sup>
    2.22
    倘
    2.13
     membentuk
    2.05
    悒
    1.86
    m
    1.85
    虽说
    1.84
     потребу
    1.83
    灕
    1.82
     has
    1.79
    从来没有
    1.78
    Activations Density 0.007%

    No Known Activations