© 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. 69391
    Prev
    Next
    INDEX
    Explanations

    victory and dominance

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

    The neuron activates on verbs that denote dominance or prevailing (e.g. “win,” “predominates”).

    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
     också
    -1.57
     also
    -1.47
    makeat
    -1.45
     a
    -1.42
    ntl
    -1.39
    coj
    -1.39
     judíos
    -1.38
     também
    -1.37
     również
    -1.37
     cristianos
    -1.34
    POSITIVE LOGITS
    Some
    1.90
    T
    1.80
     Some
    1.62
    Perhaps
    1.62
     потім
    1.54
    N
    1.52
    When
    1.50
     Perhaps
    1.49
    R
    1.48
     when
    1.46
    Activations Density 0.055%

    No Known Activations