© 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. 85746
    Prev
    Next
    INDEX
    Explanations

    actions and their objects

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

    The neuron selectively activates on verbs in their gerund or present‐participle “-ing” form.

    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
     they
    -2.50
     this
    -2.45
     it
    -2.06
     when
    -1.97
     If
    -1.92
     there
    -1.89
     if
    -1.81
     before
    -1.80
     since
    -1.71
     There
    -1.69
    POSITIVE LOGITS
    possibly
    1.65
     miniaturka
    1.64
     pourront
    1.61
     imprimer
    1.56
     pérd
    1.55
     estadounid
    1.55
     forfait
    1.55
    〬
    1.54
     rafra
    1.54
     mercredi
    1.53
    Activations Density 0.097%

    No Known Activations