© 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. 70898
    Prev
    Next
    INDEX
    Explanations

    modal verbs and verbs

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

    The neuron specializes in spotting modal auxiliary verbs (especially “should,” “will,” “would,” etc.) that express recommendation, obligation, or intent.

    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
    iterraneo
    -1.59
     seleccionados
    -1.57
     be
    -1.56
     littéraire
    -1.53
     أو
    -1.53
     głowy
    -1.52
    subaru
    -1.48
     to
    -1.48
     fueran
    -1.46
     पर
    -1.41
    POSITIVE LOGITS
    .
    1.87
    er
    1.76
     motocicleta
    1.55
     Când
    1.49
     boîtier
    1.49
    }$
    1.46
    नलिखित
    1.45
     saurait
    1.40
     bateria
    1.35
     châssis
    1.35
    Activations Density 0.019%

    No Known Activations