© 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. 34-GEMMASCOPE-RES-131K
    7. 89838
    Prev
    Next
    INDEX
    Explanations

    allow or enable actions

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

    The neuron is keyed to words that express magnitude or change—intensifiers, quantifiers, comparatives, and related degree-marking terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    hopefully
    -1.07
     hoff
    -0.90
    commande
    -0.85
    promise
    -0.84
     Maas
    -0.82
    ങ്ക
    -0.82
    消失了
    -0.80
    Hopefully
    -0.79
    проект
    -0.79
    albeit
    -0.79
    POSITIVE LOGITS
     allowing
    2.94
     allow
    2.75
     allows
    2.56
    Allow
    2.11
     enabling
    2.06
     Allowing
    1.89
     inviting
    1.89
     enables
    1.88
     Allow
    1.86
     позволя
    1.85
    Activations Density 0.059%

    No Known Activations