© 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. 129658
    Prev
    Next
    INDEX
    Explanations

    diplomatic and legal actions announced

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

    This neuron fires on the main action words (typically strong verbs) that headline articles begin with.

    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
     we
    -1.58
     our
    -1.55
     there
    -1.45
     then
    -1.41
    CHECKBOX
    -1.33
    onActivityResult
    -1.29
     conqueror
    -1.23
    LEBR
    -1.23
     automóviles
    -1.23
    irá
    -1.22
    POSITIVE LOGITS
     its
    2.28
    Its
    1.52
    its
    1.38
    其
    1.34
     itself
    1.34
    </h4>
    1.28
     Its
    1.26
    它
    1.26
    EL
    1.14
    rimônio
    1.13
    Activations Density 0.229%

    No Known Activations