© 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. 83756
    Prev
    Next
    INDEX
    Explanations

    achieving and possessing

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

    the neuron primarily activates on very common English words—especially pronouns and auxiliary verbs.

    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
    તી
    -0.85
    付费
    -0.84
    ivor
    -0.82
    获奖
    -0.82
    actually
    -0.81
     OGSÅ
    -0.81
    intended
    -0.78
     lingü
    -0.77
    他不
    -0.77
    DoNot
    -0.77
    POSITIVE LOGITS
     achieve
    1.48
     provide
    1.41
     achieving
    1.22
     achieves
    1.22
     providing
    1.20
     provides
    1.16
     achieved
    1.15
     provided
    1.14
     possess
    1.13
    Achie
    1.08
    Activations Density 0.067%

    No Known Activations