© 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. 22-GEMMASCOPE-RES-131K
    7. 54406
    Prev
    Next
    INDEX
    Explanations

    we will

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

    The neuron fires on the exact two‐letter sequence “We,” i.e. an uppercase “W” followed by “e,” such as at the start of words like “Wechsler” or “Weierstrass.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    m
    -3.13
    可以
    -3.06
    </strong>
    -2.89
    A
    -2.77
    to
    -2.77
     și
    -2.73
    up
    -2.66
    的
    -2.55
    and
    -2.53
    }$
    -2.53
    POSITIVE LOGITS
     It
    2.63
    งิน
    2.36
    嫫
    2.20
     spoluprá
    2.14
     มัน
    2.09
     projekty
    2.06
     protože
    2.05
     společnost
    2.05
    ครื่อง
    2.03
    のようです
    2.03
    Activations Density 0.060%

    No Known Activations