© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78002
    Prev
    Next
    INDEX
    Explanations

    forms of to be

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

    The neuron fires on common grammatical function words—especially pronouns (“you”) and forms of the verb “to be” (“is,” “are,” “were”) as well as modals/conjunctions like “can” and “as.”

    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
     of
    -1.23
     препратки
    -1.10
    さんから
    -1.07
    もので
    -1.06
     significantly
    -1.05
    mac
    -1.02
    bigr
    -0.99
    ().__
    -0.99
    ሖ
    -0.98
    sub
    -0.97
    POSITIVE LOGITS
     when
    1.09
    软件特色
    1.05
    懇
    1.05
    掟
    1.04
    Koala
    1.04
     in
    1.02
    dormit
    1.02
    稗
    1.00
     Aside
    1.00
    宝物
    1.00
    Activations Density 0.034%

    No Known Activations