© 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. 10-GEMMASCOPE-RES-131K
    7. 38740
    Prev
    Next
    INDEX
    Explanations

    how could

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

    The neuron activates strongly on the modal verb “could,” especially in question or hypothetical contexts.

    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
    </i>
    -1.84
     pouze
    -1.59
     делает
    -1.59
    綵
    -1.56
    vgili
    -1.52
    </h3>
    -1.50
    เพราะ
    -1.50
    ⢌
    -1.49
    bộ
    -1.48
    𝔴
    -1.48
    POSITIVE LOGITS
    )
    2.17
    ⓦ
    1.76
    1.74
    凩
    1.70
     harte
    1.68
     brille
    1.65
    k
    1.64
    ’
    1.64
    苼
    1.63
    觧
    1.63
    Activations Density 0.063%

    No Known Activations