© 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. 65495
    Prev
    Next
    INDEX
    Explanations

    verb followed by it or this

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

    The neuron responds to common verbs (especially basic action verbs like “find,” “use,” “open,” “make,” “place,” etc.).

    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
     
    -1.56
    .
    -1.55
     cuyos
    -1.52
     "
    -1.52
    ,
    -1.48
     cuyo
    -1.45
    Their
    -1.42
     I
    -1.39
        
    -1.38
     T
    -1.38
    POSITIVE LOGITS
     it
    7.19
     them
    4.06
    它
    2.38
     this
    2.08
     kulak
    1.88
     him
    1.80
     उसे
    1.77
     its
    1.77
     нём
    1.76
     آن‌ها
    1.75
    Activations Density 0.222%

    No Known Activations