© 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. 22-GEMMASCOPE-RES-131K
    7. 73017
    Prev
    Next
    INDEX
    Explanations

    it followed by verbs

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

    The neuron primarily fires on the standalone pronoun “it” (in any case) when it appears in the text.

    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
     tersenyum
    -1.25
     tertawa
    -1.23
    льевич
    -1.23
     mengenakan
    -1.13
     Serbie
    -1.11
     particulier
    -1.10
    charest
    -1.09
     memenangkan
    -1.04
    calls
    -1.03
     ۱۱
    -1.03
    POSITIVE LOGITS
     so
    1.27
     include
    1.23
     will
    1.21
     dotyczy
    1.16
     because
    1.12
     when
    1.11
     can
    1.05
     also
    1.02
     potrzeby
    1.01
     involves
    0.98
    Activations Density 0.087%

    No Known Activations