© 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. 10-GEMMASCOPE-RES-131K
    7. 12963
    Prev
    Next
    INDEX
    Explanations

    is/has followed by action

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

    The neuron fires on common auxiliary verbs (forms of “to be” and “to have,” e.g. is, are, has, were).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    larınız
    -1.51
     and
    -1.39
     will
    -1.37
    cellona
    -1.24
    ㄋ
    -1.20
     achieved
    -1.20
     capacity
    -1.19
     elegir
    -1.19
     ensured
    -1.18
    dă
    -1.18
    POSITIVE LOGITS
     not
    2.17
    他们
    1.84
    
    1.80
    ⃨
    1.71
     Reſ
    1.66
     vokal
    1.65
     disiplin
    1.61
    殛
    1.60
     terle
    1.56
     ſont
    1.54
    Activations Density 0.129%

    No Known Activations