© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90777
    Prev
    Next
    INDEX
    Explanations

    time and circumstance clauses

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

    The neuron detects the temporal conjunction “when” (or phrases indicating a specific point in time) introducing time clauses.

    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
    }
    -2.14
    ]
    -1.99
    )
    -1.97
     было
    -1.63
     рисунки
    -1.54
    ांकि
    -1.53
    メス
    -1.52
     that
    -1.52
     decim
    -1.51
     möjlighet
    -1.49
    POSITIVE LOGITS
    L
    1.86
     gbc
    1.84
    ächst
    1.55
    辂
    1.55
    ань
    1.55
    ÍAS
    1.53
    
    1.52
     âgées
    1.52
    گانه
    1.52
    INATION
    1.52
    Activations Density 0.017%

    No Known Activations