© 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. 60409
    Prev
    Next
    INDEX
    Explanations

    causal or temporal clauses

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

    The neuron is firing on common auxiliary and copular verbs—especially different forms of “be” and “have.”

    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
    踮
    -1.10
    一旁的
    -1.06
    uliert
    -1.06
    Meik
    -1.05
     was
    -1.02
    看了看
    -1.02
    哭了
    -1.02
     terá
    -1.01
    виси
    -1.01
     at
    -1.00
    POSITIVE LOGITS
     because
    1.62
     while
    1.48
     Because
    1.41
     karena
    1.39
     from
    1.28
     ponieważ
    1.27
     kerana
    1.18
     Männern
    1.17
     gdy
    1.16
    꼼
    1.16
    Activations Density 0.196%

    No Known Activations