© 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. 20740
    Prev
    Next
    INDEX
    Explanations

    states and actions

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

    The neuron flags longer English words that end in common suffixes like ‑ion, ‑ing, ‑ed, and ‑ly.

    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
     that
    -1.63
     and
    -1.55
     namn
    -1.48
    ズニー
    -1.41
    随着
    -1.34
    嗵
    -1.32
     månader
    -1.30
     dagar
    -1.29
     Finlande
    -1.28
     sidan
    -1.26
    POSITIVE LOGITS
     contrário
    1.57
    two
    1.57
    type
    1.56
     view
    1.48
     powiet
    1.40
     not
    1.37
     argument
    1.34
    惇
    1.34
     primeiro
    1.32
     pertenec
    1.31
    Activations Density 0.063%

    No Known Activations