© 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. 12739
    Prev
    Next
    INDEX
    Explanations

    up or back followed by preposition

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

    The neuron strongly activates on the particle “up” (and closely related forms like “upon”)—i.e. it flags instances of “up” in phrasal verbs or compounds.

    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
     \
    -1.77
     —
    -1.72
    
    -1.68
    将她
    -1.62
     många
    -1.60
     ava
    -1.47
     \_
    -1.45
     Frequently
    -1.44
     cushioning
    -1.44
     voltar
    -1.43
    POSITIVE LOGITS
    たちの
    1.95
    憮
    1.84
    塤
    1.84
     obiettivi
    1.81
     respective
    1.80
     beserta
    1.79
     μόνο
    1.77
     Also
    1.77
    刋
    1.77
    搴
    1.76
    Activations Density 0.001%

    No Known Activations