© 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. 22-GEMMASCOPE-RES-131K
    7. 27331
    Prev
    Next
    INDEX
    Explanations

    to + verb necessity

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

    The neuron is responding to very high-frequency function words (common auxiliaries, prepositions, and other stopwords).

    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
     this
    -1.50
     that
    -1.37
     any
    -1.34
     if
    -1.24
     can
    -1.20
     how
    -1.20
     what
    -1.16
     appears
    -1.14
     could
    -1.14
     has
    -1.14
    POSITIVE LOGITS
     to
    1.66
     пришлось
    1.28
     vaak
    1.20
     VERY
    1.08
     приходится
    1.07
     recurrir
    1.04
     choisir
    1.02
     بسبب
    1.02
     esencial
    1.00
    //!
    1.00
    Activations Density 0.033%

    No Known Activations