© 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. 129713
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to past-tense verbs (especially forms of “to be” like “was”/“were” and other verbs marked for past tense).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    creation, establishment, or development

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     continúa
    -1.41
     ofrece
    -1.20
     utilisés
    -1.19
    indicated
    -1.15
     sigue
    -1.13
    lenia
    -1.09
     vuelve
    -1.08
     revamped
    -1.08
    hawar
    -1.08
    िल्ली
    -1.06
    POSITIVE LOGITS
     created
    1.62
     establish
    1.34
     creation
    1.31
     established
    1.23
     emerge
    1.21
    عارف
    1.16
    亮点
    1.14
     create
    1.14
     existence
    1.13
     emerges
    1.10
    Activations Density 0.126%

    No Known Activations