© 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. 14054
    Prev
    Next
    INDEX
    Explanations

    makes sense or consequence

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

    The neuron specializes in spotting uses of the verb “make” (including its inflected form “makes”).

    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
    tigste
    -1.01
    YN
    -1.01
    сия
    -0.98
    炽
    -0.98
     it
    -0.96
     aquest
    -0.94
    лі
    -0.93
     són
    -0.93
     the
    -0.92
     this
    -0.92
    POSITIVE LOGITS
    Would
    1.12
    荩
    1.07
     pozdě
    1.06
     you
    1.03
     Drei
    1.03
     Makes
    1.02
     sosteniendo
    1.02
     nervous
    1.01
     way
    1.01
     would
    0.99
    Activations Density 0.045%

    No Known Activations