© 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. 7545
    Prev
    Next
    INDEX
    Explanations

    what x is

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

    The neuron strongly activates on occurrences of the copular verb “to be” (especially “is” and “are”).

    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
     gantung
    -2.03
    给人
    -1.99
    </td>
    -1.94
     DISEASES
    -1.94
    歺
    -1.90
     neuer
    -1.89
    给我们
    -1.88
     tejto
    -1.85
    ſſen
    -1.84
     masculinos
    -1.84
    POSITIVE LOGITS
    </strong>
    2.66
    </h1>
    2.20
     a
    2.09
     in
    2.08
    '
    1.82
            
    1.78
    T
    1.66
     on
    1.60
    H
    1.59
    *
    1.58
    Activations Density 0.021%

    No Known Activations