© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130449
    Prev
    Next
    INDEX
    Explanations

    meant to do

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

    The neuron strongly activates on the infinitival “to” (especially in “X meant to/ask to/write to/…”) marking the start of an intended action.

    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
    because
    -1.99
    after
    -1.78
    ಞ
    -1.76
    ⩩
    -1.64
     Eigentü
    -1.61
    When
    -1.61
     with
    -1.61
    -1.57
     damaged
    -1.55
     когда
    -1.55
    POSITIVE LOGITS
    /
    1.95
     schien
    1.47
    或
    1.46
     also
    1.46
     veya
    1.44
     originally
    1.41
     be
    1.41
    诋
    1.41
     étrange
    1.41
    on
    1.40
    Activations Density 0.009%

    No Known Activations