© 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. 86920
    Prev
    Next
    INDEX
    Explanations

    compose and composition

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

    This neuron activates strongly on the root “compos” and its morphological variants (e.g. compose, composed, composing, composer, composition).

    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
    硨
    -2.69
     creat
    -2.17
     categor
    -2.08
    withCredentials
    -2.06
     placid
    -2.05
    𐬹
    -2.05
    裥
    -2.05
     chris
    -2.03
     are
    -2.03
     benevol
    -2.02
    POSITIVE LOGITS
    ↵
    2.44
     When
    2.41
     While
    2.06
    剮
    2.06
     белой
    2.05
     an
    2.02
     philosophie
    1.88
      
    1.88
    a
    1.88
    萦
    1.84
    Activations Density 0.025%

    No Known Activations